Upload 12 files
Browse files- .gitattributes +1 -0
- README.md +65 -3
- all_results.json +18 -0
- config.json +35 -0
- eval_results.json +11 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +63 -0
- train_results.json +11 -0
- trainer_state.json +1998 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,3 +1,65 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: agentlans/multilingual-e5-small-aligned-v2
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: multilingual-e5-small-aligned-v2-fineweb2hq-vs-c4-classifier-run2
|
| 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 |
+
# multilingual-e5-small-aligned-v2-fineweb2hq-vs-c4-classifier-run2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [agentlans/multilingual-e5-small-aligned-v2](https://huggingface.co/agentlans/multilingual-e5-small-aligned-v2) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1983
|
| 22 |
+
- Accuracy: 0.9515
|
| 23 |
+
- Combined Score: 1.3494
|
| 24 |
+
- Num Input Tokens Seen: 122880000
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 3.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Combined Score | Input Tokens Seen |
|
| 54 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:--------------:|:-----------------:|
|
| 55 |
+
| 0.1387 | 1.0 | 40000 | 0.1983 | 0.9515 | 1.3494 | 40960000 |
|
| 56 |
+
| 0.0682 | 2.0 | 80000 | 0.2264 | 0.9528 | 1.3270 | 81920000 |
|
| 57 |
+
| 0.0424 | 3.0 | 120000 | 0.2598 | 0.9552 | 1.2845 | 122880000 |
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- Transformers 4.51.3
|
| 63 |
+
- Pytorch 2.6.0+cu124
|
| 64 |
+
- Datasets 3.2.0
|
| 65 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.951525,
|
| 4 |
+
"eval_combined_score": 1.3493705490187269,
|
| 5 |
+
"eval_loss": 0.198301300406456,
|
| 6 |
+
"eval_runtime": 39.4383,
|
| 7 |
+
"eval_samples": 80000,
|
| 8 |
+
"eval_samples_per_second": 2028.484,
|
| 9 |
+
"eval_steps_per_second": 253.56,
|
| 10 |
+
"num_input_tokens_seen": 122880000,
|
| 11 |
+
"total_flos": 1.580945522688e+16,
|
| 12 |
+
"train_loss": 0.10143799341519674,
|
| 13 |
+
"train_runtime": 4258.2582,
|
| 14 |
+
"train_samples": 320000,
|
| 15 |
+
"train_samples_per_second": 225.444,
|
| 16 |
+
"train_steps_per_second": 28.181,
|
| 17 |
+
"train_tokens_per_second": 28856.869
|
| 18 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"finetuning_task": "text-classification",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 384,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "allenai/c4",
|
| 13 |
+
"1": "epfml/FineWeb2-HQ"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 1536,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"allenai/c4": 0,
|
| 19 |
+
"epfml/FineWeb2-HQ": 1
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.51.3",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 250037
|
| 35 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.951525,
|
| 4 |
+
"eval_combined_score": 1.3493705490187269,
|
| 5 |
+
"eval_loss": 0.198301300406456,
|
| 6 |
+
"eval_runtime": 39.4383,
|
| 7 |
+
"eval_samples": 80000,
|
| 8 |
+
"eval_samples_per_second": 2028.484,
|
| 9 |
+
"eval_steps_per_second": 253.56,
|
| 10 |
+
"num_input_tokens_seen": 122880000
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a782718093971379b07049ef94b53c8d53503dcc43332958d0f4ab146b3308f
|
| 3 |
+
size 470641664
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 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": "</s>",
|
| 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": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e2c4647474659095b757711e8aef0583d58dbb50e3349958ebc460a9cf4977
|
| 3 |
+
size 17083065
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 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": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 512,
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
+
"sp_model_kwargs": {},
|
| 58 |
+
"stride": 0,
|
| 59 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 60 |
+
"truncation_side": "right",
|
| 61 |
+
"truncation_strategy": "longest_first",
|
| 62 |
+
"unk_token": "<unk>"
|
| 63 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"num_input_tokens_seen": 122880000,
|
| 4 |
+
"total_flos": 1.580945522688e+16,
|
| 5 |
+
"train_loss": 0.10143799341519674,
|
| 6 |
+
"train_runtime": 4258.2582,
|
| 7 |
+
"train_samples": 320000,
|
| 8 |
+
"train_samples_per_second": 225.444,
|
| 9 |
+
"train_steps_per_second": 28.181,
|
| 10 |
+
"train_tokens_per_second": 28856.869
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1998 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 40000,
|
| 3 |
+
"best_metric": 0.198301300406456,
|
| 4 |
+
"best_model_checkpoint": "/media/user/Expansion1/multilingual-e5-small-aligned-v2-fineweb2hq-vs-c4-classifier-run2/checkpoint-40000",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 120000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0125,
|
| 14 |
+
"grad_norm": 5.874658584594727,
|
| 15 |
+
"learning_rate": 4.979208333333333e-05,
|
| 16 |
+
"loss": 0.3436,
|
| 17 |
+
"num_input_tokens_seen": 512000,
|
| 18 |
+
"step": 500
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.025,
|
| 22 |
+
"grad_norm": 0.6375065445899963,
|
| 23 |
+
"learning_rate": 4.958375e-05,
|
| 24 |
+
"loss": 0.281,
|
| 25 |
+
"num_input_tokens_seen": 1024000,
|
| 26 |
+
"step": 1000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.0375,
|
| 30 |
+
"grad_norm": 0.48116546869277954,
|
| 31 |
+
"learning_rate": 4.937541666666667e-05,
|
| 32 |
+
"loss": 0.2595,
|
| 33 |
+
"num_input_tokens_seen": 1536000,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.05,
|
| 38 |
+
"grad_norm": 0.6305193305015564,
|
| 39 |
+
"learning_rate": 4.9167083333333336e-05,
|
| 40 |
+
"loss": 0.2466,
|
| 41 |
+
"num_input_tokens_seen": 2048000,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0625,
|
| 46 |
+
"grad_norm": 3.560100555419922,
|
| 47 |
+
"learning_rate": 4.8958750000000006e-05,
|
| 48 |
+
"loss": 0.2283,
|
| 49 |
+
"num_input_tokens_seen": 2560000,
|
| 50 |
+
"step": 2500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.075,
|
| 54 |
+
"grad_norm": 43.007347106933594,
|
| 55 |
+
"learning_rate": 4.875041666666667e-05,
|
| 56 |
+
"loss": 0.2106,
|
| 57 |
+
"num_input_tokens_seen": 3072000,
|
| 58 |
+
"step": 3000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0875,
|
| 62 |
+
"grad_norm": 27.75348472595215,
|
| 63 |
+
"learning_rate": 4.854208333333334e-05,
|
| 64 |
+
"loss": 0.2198,
|
| 65 |
+
"num_input_tokens_seen": 3584000,
|
| 66 |
+
"step": 3500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1,
|
| 70 |
+
"grad_norm": 0.11089582741260529,
|
| 71 |
+
"learning_rate": 4.833375e-05,
|
| 72 |
+
"loss": 0.2145,
|
| 73 |
+
"num_input_tokens_seen": 4096000,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.1125,
|
| 78 |
+
"grad_norm": 0.08869020640850067,
|
| 79 |
+
"learning_rate": 4.812541666666667e-05,
|
| 80 |
+
"loss": 0.2033,
|
| 81 |
+
"num_input_tokens_seen": 4608000,
|
| 82 |
+
"step": 4500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.125,
|
| 86 |
+
"grad_norm": 22.97330665588379,
|
| 87 |
+
"learning_rate": 4.791708333333333e-05,
|
| 88 |
+
"loss": 0.2007,
|
| 89 |
+
"num_input_tokens_seen": 5120000,
|
| 90 |
+
"step": 5000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.1375,
|
| 94 |
+
"grad_norm": 0.12722039222717285,
|
| 95 |
+
"learning_rate": 4.770875e-05,
|
| 96 |
+
"loss": 0.1893,
|
| 97 |
+
"num_input_tokens_seen": 5632000,
|
| 98 |
+
"step": 5500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.15,
|
| 102 |
+
"grad_norm": 24.923276901245117,
|
| 103 |
+
"learning_rate": 4.750041666666667e-05,
|
| 104 |
+
"loss": 0.2073,
|
| 105 |
+
"num_input_tokens_seen": 6144000,
|
| 106 |
+
"step": 6000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.1625,
|
| 110 |
+
"grad_norm": 0.17447435855865479,
|
| 111 |
+
"learning_rate": 4.729208333333334e-05,
|
| 112 |
+
"loss": 0.2024,
|
| 113 |
+
"num_input_tokens_seen": 6656000,
|
| 114 |
+
"step": 6500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.175,
|
| 118 |
+
"grad_norm": 5.2057671546936035,
|
| 119 |
+
"learning_rate": 4.708375e-05,
|
| 120 |
+
"loss": 0.2168,
|
| 121 |
+
"num_input_tokens_seen": 7168000,
|
| 122 |
+
"step": 7000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1875,
|
| 126 |
+
"grad_norm": 0.35154542326927185,
|
| 127 |
+
"learning_rate": 4.687541666666667e-05,
|
| 128 |
+
"loss": 0.2002,
|
| 129 |
+
"num_input_tokens_seen": 7680000,
|
| 130 |
+
"step": 7500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2,
|
| 134 |
+
"grad_norm": 0.17855411767959595,
|
| 135 |
+
"learning_rate": 4.6667083333333336e-05,
|
| 136 |
+
"loss": 0.1863,
|
| 137 |
+
"num_input_tokens_seen": 8192000,
|
| 138 |
+
"step": 8000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.2125,
|
| 142 |
+
"grad_norm": 0.26302626729011536,
|
| 143 |
+
"learning_rate": 4.645875e-05,
|
| 144 |
+
"loss": 0.2023,
|
| 145 |
+
"num_input_tokens_seen": 8704000,
|
| 146 |
+
"step": 8500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.225,
|
| 150 |
+
"grad_norm": 1.0355998277664185,
|
| 151 |
+
"learning_rate": 4.625041666666667e-05,
|
| 152 |
+
"loss": 0.1996,
|
| 153 |
+
"num_input_tokens_seen": 9216000,
|
| 154 |
+
"step": 9000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.2375,
|
| 158 |
+
"grad_norm": 3.5437514781951904,
|
| 159 |
+
"learning_rate": 4.6042083333333334e-05,
|
| 160 |
+
"loss": 0.1928,
|
| 161 |
+
"num_input_tokens_seen": 9728000,
|
| 162 |
+
"step": 9500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.25,
|
| 166 |
+
"grad_norm": 18.394441604614258,
|
| 167 |
+
"learning_rate": 4.5833750000000005e-05,
|
| 168 |
+
"loss": 0.1968,
|
| 169 |
+
"num_input_tokens_seen": 10240000,
|
| 170 |
+
"step": 10000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2625,
|
| 174 |
+
"grad_norm": 2.9275922775268555,
|
| 175 |
+
"learning_rate": 4.562541666666667e-05,
|
| 176 |
+
"loss": 0.2081,
|
| 177 |
+
"num_input_tokens_seen": 10752000,
|
| 178 |
+
"step": 10500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.275,
|
| 182 |
+
"grad_norm": 3.922402858734131,
|
| 183 |
+
"learning_rate": 4.541708333333334e-05,
|
| 184 |
+
"loss": 0.1769,
|
| 185 |
+
"num_input_tokens_seen": 11264000,
|
| 186 |
+
"step": 11000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.2875,
|
| 190 |
+
"grad_norm": 0.25219565629959106,
|
| 191 |
+
"learning_rate": 4.5208749999999996e-05,
|
| 192 |
+
"loss": 0.1722,
|
| 193 |
+
"num_input_tokens_seen": 11776000,
|
| 194 |
+
"step": 11500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.3,
|
| 198 |
+
"grad_norm": 0.10917416214942932,
|
| 199 |
+
"learning_rate": 4.500041666666667e-05,
|
| 200 |
+
"loss": 0.1638,
|
| 201 |
+
"num_input_tokens_seen": 12288000,
|
| 202 |
+
"step": 12000
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.3125,
|
| 206 |
+
"grad_norm": 0.1928466558456421,
|
| 207 |
+
"learning_rate": 4.479208333333334e-05,
|
| 208 |
+
"loss": 0.1826,
|
| 209 |
+
"num_input_tokens_seen": 12800000,
|
| 210 |
+
"step": 12500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.325,
|
| 214 |
+
"grad_norm": 1.1688095331192017,
|
| 215 |
+
"learning_rate": 4.458375e-05,
|
| 216 |
+
"loss": 0.186,
|
| 217 |
+
"num_input_tokens_seen": 13312000,
|
| 218 |
+
"step": 13000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.3375,
|
| 222 |
+
"grad_norm": 0.07879551500082016,
|
| 223 |
+
"learning_rate": 4.437541666666667e-05,
|
| 224 |
+
"loss": 0.1638,
|
| 225 |
+
"num_input_tokens_seen": 13824000,
|
| 226 |
+
"step": 13500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.35,
|
| 230 |
+
"grad_norm": 1.294481635093689,
|
| 231 |
+
"learning_rate": 4.4167083333333336e-05,
|
| 232 |
+
"loss": 0.1695,
|
| 233 |
+
"num_input_tokens_seen": 14336000,
|
| 234 |
+
"step": 14000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3625,
|
| 238 |
+
"grad_norm": 21.836345672607422,
|
| 239 |
+
"learning_rate": 4.395875000000001e-05,
|
| 240 |
+
"loss": 0.1713,
|
| 241 |
+
"num_input_tokens_seen": 14848000,
|
| 242 |
+
"step": 14500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.375,
|
| 246 |
+
"grad_norm": 0.1329026073217392,
|
| 247 |
+
"learning_rate": 4.375041666666667e-05,
|
| 248 |
+
"loss": 0.178,
|
| 249 |
+
"num_input_tokens_seen": 15360000,
|
| 250 |
+
"step": 15000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3875,
|
| 254 |
+
"grad_norm": 2.196962594985962,
|
| 255 |
+
"learning_rate": 4.3542083333333334e-05,
|
| 256 |
+
"loss": 0.1616,
|
| 257 |
+
"num_input_tokens_seen": 15872000,
|
| 258 |
+
"step": 15500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.4,
|
| 262 |
+
"grad_norm": 0.06707575172185898,
|
| 263 |
+
"learning_rate": 4.333375e-05,
|
| 264 |
+
"loss": 0.1563,
|
| 265 |
+
"num_input_tokens_seen": 16384000,
|
| 266 |
+
"step": 16000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.4125,
|
| 270 |
+
"grad_norm": 4.03335428237915,
|
| 271 |
+
"learning_rate": 4.312541666666667e-05,
|
| 272 |
+
"loss": 0.1644,
|
| 273 |
+
"num_input_tokens_seen": 16896000,
|
| 274 |
+
"step": 16500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.425,
|
| 278 |
+
"grad_norm": 0.7723323702812195,
|
| 279 |
+
"learning_rate": 4.291708333333333e-05,
|
| 280 |
+
"loss": 0.1695,
|
| 281 |
+
"num_input_tokens_seen": 17408000,
|
| 282 |
+
"step": 17000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4375,
|
| 286 |
+
"grad_norm": 0.14005227386951447,
|
| 287 |
+
"learning_rate": 4.270875e-05,
|
| 288 |
+
"loss": 0.1771,
|
| 289 |
+
"num_input_tokens_seen": 17920000,
|
| 290 |
+
"step": 17500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.45,
|
| 294 |
+
"grad_norm": 0.22879253327846527,
|
| 295 |
+
"learning_rate": 4.250041666666667e-05,
|
| 296 |
+
"loss": 0.1652,
|
| 297 |
+
"num_input_tokens_seen": 18432000,
|
| 298 |
+
"step": 18000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.4625,
|
| 302 |
+
"grad_norm": 41.407352447509766,
|
| 303 |
+
"learning_rate": 4.229208333333334e-05,
|
| 304 |
+
"loss": 0.1697,
|
| 305 |
+
"num_input_tokens_seen": 18944000,
|
| 306 |
+
"step": 18500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.475,
|
| 310 |
+
"grad_norm": 0.2552178204059601,
|
| 311 |
+
"learning_rate": 4.208375e-05,
|
| 312 |
+
"loss": 0.169,
|
| 313 |
+
"num_input_tokens_seen": 19456000,
|
| 314 |
+
"step": 19000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.4875,
|
| 318 |
+
"grad_norm": 4.208723545074463,
|
| 319 |
+
"learning_rate": 4.1875416666666666e-05,
|
| 320 |
+
"loss": 0.1887,
|
| 321 |
+
"num_input_tokens_seen": 19968000,
|
| 322 |
+
"step": 19500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.5,
|
| 326 |
+
"grad_norm": 0.6019179821014404,
|
| 327 |
+
"learning_rate": 4.1667083333333336e-05,
|
| 328 |
+
"loss": 0.149,
|
| 329 |
+
"num_input_tokens_seen": 20480000,
|
| 330 |
+
"step": 20000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.5125,
|
| 334 |
+
"grad_norm": 11.652756690979004,
|
| 335 |
+
"learning_rate": 4.145875e-05,
|
| 336 |
+
"loss": 0.1485,
|
| 337 |
+
"num_input_tokens_seen": 20992000,
|
| 338 |
+
"step": 20500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.525,
|
| 342 |
+
"grad_norm": 3.790767192840576,
|
| 343 |
+
"learning_rate": 4.125041666666667e-05,
|
| 344 |
+
"loss": 0.1613,
|
| 345 |
+
"num_input_tokens_seen": 21504000,
|
| 346 |
+
"step": 21000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5375,
|
| 350 |
+
"grad_norm": 0.0643579512834549,
|
| 351 |
+
"learning_rate": 4.1042083333333335e-05,
|
| 352 |
+
"loss": 0.156,
|
| 353 |
+
"num_input_tokens_seen": 22016000,
|
| 354 |
+
"step": 21500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.55,
|
| 358 |
+
"grad_norm": 6.347803115844727,
|
| 359 |
+
"learning_rate": 4.0833750000000005e-05,
|
| 360 |
+
"loss": 0.1743,
|
| 361 |
+
"num_input_tokens_seen": 22528000,
|
| 362 |
+
"step": 22000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.5625,
|
| 366 |
+
"grad_norm": 0.45395129919052124,
|
| 367 |
+
"learning_rate": 4.062541666666667e-05,
|
| 368 |
+
"loss": 0.1566,
|
| 369 |
+
"num_input_tokens_seen": 23040000,
|
| 370 |
+
"step": 22500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.575,
|
| 374 |
+
"grad_norm": 4.8587470054626465,
|
| 375 |
+
"learning_rate": 4.041708333333333e-05,
|
| 376 |
+
"loss": 0.156,
|
| 377 |
+
"num_input_tokens_seen": 23552000,
|
| 378 |
+
"step": 23000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.5875,
|
| 382 |
+
"grad_norm": 0.8771836757659912,
|
| 383 |
+
"learning_rate": 4.0208750000000004e-05,
|
| 384 |
+
"loss": 0.1473,
|
| 385 |
+
"num_input_tokens_seen": 24064000,
|
| 386 |
+
"step": 23500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.6,
|
| 390 |
+
"grad_norm": 7.632213592529297,
|
| 391 |
+
"learning_rate": 4.000041666666667e-05,
|
| 392 |
+
"loss": 0.1523,
|
| 393 |
+
"num_input_tokens_seen": 24576000,
|
| 394 |
+
"step": 24000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6125,
|
| 398 |
+
"grad_norm": 4.013466835021973,
|
| 399 |
+
"learning_rate": 3.979208333333334e-05,
|
| 400 |
+
"loss": 0.1646,
|
| 401 |
+
"num_input_tokens_seen": 25088000,
|
| 402 |
+
"step": 24500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.625,
|
| 406 |
+
"grad_norm": 0.08471076935529709,
|
| 407 |
+
"learning_rate": 3.958375e-05,
|
| 408 |
+
"loss": 0.1653,
|
| 409 |
+
"num_input_tokens_seen": 25600000,
|
| 410 |
+
"step": 25000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.6375,
|
| 414 |
+
"grad_norm": 4.263392448425293,
|
| 415 |
+
"learning_rate": 3.937541666666667e-05,
|
| 416 |
+
"loss": 0.1513,
|
| 417 |
+
"num_input_tokens_seen": 26112000,
|
| 418 |
+
"step": 25500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.65,
|
| 422 |
+
"grad_norm": 17.002439498901367,
|
| 423 |
+
"learning_rate": 3.9167083333333336e-05,
|
| 424 |
+
"loss": 0.144,
|
| 425 |
+
"num_input_tokens_seen": 26624000,
|
| 426 |
+
"step": 26000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6625,
|
| 430 |
+
"grad_norm": 0.056964244693517685,
|
| 431 |
+
"learning_rate": 3.895875e-05,
|
| 432 |
+
"loss": 0.1517,
|
| 433 |
+
"num_input_tokens_seen": 27136000,
|
| 434 |
+
"step": 26500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.675,
|
| 438 |
+
"grad_norm": 0.4403606653213501,
|
| 439 |
+
"learning_rate": 3.8750416666666664e-05,
|
| 440 |
+
"loss": 0.1501,
|
| 441 |
+
"num_input_tokens_seen": 27648000,
|
| 442 |
+
"step": 27000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.6875,
|
| 446 |
+
"grad_norm": 0.11431742459535599,
|
| 447 |
+
"learning_rate": 3.8542083333333335e-05,
|
| 448 |
+
"loss": 0.1597,
|
| 449 |
+
"num_input_tokens_seen": 28160000,
|
| 450 |
+
"step": 27500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7,
|
| 454 |
+
"grad_norm": 7.810299396514893,
|
| 455 |
+
"learning_rate": 3.833375e-05,
|
| 456 |
+
"loss": 0.1437,
|
| 457 |
+
"num_input_tokens_seen": 28672000,
|
| 458 |
+
"step": 28000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7125,
|
| 462 |
+
"grad_norm": 5.501016616821289,
|
| 463 |
+
"learning_rate": 3.812541666666667e-05,
|
| 464 |
+
"loss": 0.1415,
|
| 465 |
+
"num_input_tokens_seen": 29184000,
|
| 466 |
+
"step": 28500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.725,
|
| 470 |
+
"grad_norm": 0.20471607148647308,
|
| 471 |
+
"learning_rate": 3.791708333333333e-05,
|
| 472 |
+
"loss": 0.1545,
|
| 473 |
+
"num_input_tokens_seen": 29696000,
|
| 474 |
+
"step": 29000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.7375,
|
| 478 |
+
"grad_norm": 4.6759748458862305,
|
| 479 |
+
"learning_rate": 3.7708750000000004e-05,
|
| 480 |
+
"loss": 0.1431,
|
| 481 |
+
"num_input_tokens_seen": 30208000,
|
| 482 |
+
"step": 29500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.75,
|
| 486 |
+
"grad_norm": 0.12430200725793839,
|
| 487 |
+
"learning_rate": 3.7500416666666674e-05,
|
| 488 |
+
"loss": 0.1337,
|
| 489 |
+
"num_input_tokens_seen": 30720000,
|
| 490 |
+
"step": 30000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.7625,
|
| 494 |
+
"grad_norm": 0.19309231638908386,
|
| 495 |
+
"learning_rate": 3.729208333333333e-05,
|
| 496 |
+
"loss": 0.1338,
|
| 497 |
+
"num_input_tokens_seen": 31232000,
|
| 498 |
+
"step": 30500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.775,
|
| 502 |
+
"grad_norm": 0.18272100389003754,
|
| 503 |
+
"learning_rate": 3.708375e-05,
|
| 504 |
+
"loss": 0.1504,
|
| 505 |
+
"num_input_tokens_seen": 31744000,
|
| 506 |
+
"step": 31000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7875,
|
| 510 |
+
"grad_norm": 0.08077079057693481,
|
| 511 |
+
"learning_rate": 3.6875416666666666e-05,
|
| 512 |
+
"loss": 0.13,
|
| 513 |
+
"num_input_tokens_seen": 32256000,
|
| 514 |
+
"step": 31500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8,
|
| 518 |
+
"grad_norm": 0.3213728368282318,
|
| 519 |
+
"learning_rate": 3.666708333333334e-05,
|
| 520 |
+
"loss": 0.1406,
|
| 521 |
+
"num_input_tokens_seen": 32768000,
|
| 522 |
+
"step": 32000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.8125,
|
| 526 |
+
"grad_norm": 2.6233737468719482,
|
| 527 |
+
"learning_rate": 3.645875e-05,
|
| 528 |
+
"loss": 0.1435,
|
| 529 |
+
"num_input_tokens_seen": 33280000,
|
| 530 |
+
"step": 32500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.825,
|
| 534 |
+
"grad_norm": 0.1083766371011734,
|
| 535 |
+
"learning_rate": 3.625041666666667e-05,
|
| 536 |
+
"loss": 0.1361,
|
| 537 |
+
"num_input_tokens_seen": 33792000,
|
| 538 |
+
"step": 33000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.8375,
|
| 542 |
+
"grad_norm": 0.08282948285341263,
|
| 543 |
+
"learning_rate": 3.6042083333333335e-05,
|
| 544 |
+
"loss": 0.1483,
|
| 545 |
+
"num_input_tokens_seen": 34304000,
|
| 546 |
+
"step": 33500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.85,
|
| 550 |
+
"grad_norm": 0.10612857341766357,
|
| 551 |
+
"learning_rate": 3.583375e-05,
|
| 552 |
+
"loss": 0.1419,
|
| 553 |
+
"num_input_tokens_seen": 34816000,
|
| 554 |
+
"step": 34000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.8625,
|
| 558 |
+
"grad_norm": 1.134366750717163,
|
| 559 |
+
"learning_rate": 3.562541666666667e-05,
|
| 560 |
+
"loss": 0.1381,
|
| 561 |
+
"num_input_tokens_seen": 35328000,
|
| 562 |
+
"step": 34500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.875,
|
| 566 |
+
"grad_norm": 32.71923065185547,
|
| 567 |
+
"learning_rate": 3.5417083333333333e-05,
|
| 568 |
+
"loss": 0.1395,
|
| 569 |
+
"num_input_tokens_seen": 35840000,
|
| 570 |
+
"step": 35000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8875,
|
| 574 |
+
"grad_norm": 0.14211738109588623,
|
| 575 |
+
"learning_rate": 3.5208750000000004e-05,
|
| 576 |
+
"loss": 0.1543,
|
| 577 |
+
"num_input_tokens_seen": 36352000,
|
| 578 |
+
"step": 35500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.9,
|
| 582 |
+
"grad_norm": 0.04908756539225578,
|
| 583 |
+
"learning_rate": 3.500041666666667e-05,
|
| 584 |
+
"loss": 0.1229,
|
| 585 |
+
"num_input_tokens_seen": 36864000,
|
| 586 |
+
"step": 36000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.9125,
|
| 590 |
+
"grad_norm": 0.47926560044288635,
|
| 591 |
+
"learning_rate": 3.479208333333334e-05,
|
| 592 |
+
"loss": 0.1251,
|
| 593 |
+
"num_input_tokens_seen": 37376000,
|
| 594 |
+
"step": 36500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.925,
|
| 598 |
+
"grad_norm": 1.389073371887207,
|
| 599 |
+
"learning_rate": 3.458375e-05,
|
| 600 |
+
"loss": 0.1718,
|
| 601 |
+
"num_input_tokens_seen": 37888000,
|
| 602 |
+
"step": 37000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.9375,
|
| 606 |
+
"grad_norm": 0.14962467551231384,
|
| 607 |
+
"learning_rate": 3.437541666666667e-05,
|
| 608 |
+
"loss": 0.1579,
|
| 609 |
+
"num_input_tokens_seen": 38400000,
|
| 610 |
+
"step": 37500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.95,
|
| 614 |
+
"grad_norm": 3.8970487117767334,
|
| 615 |
+
"learning_rate": 3.416708333333333e-05,
|
| 616 |
+
"loss": 0.1294,
|
| 617 |
+
"num_input_tokens_seen": 38912000,
|
| 618 |
+
"step": 38000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9625,
|
| 622 |
+
"grad_norm": 0.1765402853488922,
|
| 623 |
+
"learning_rate": 3.395875e-05,
|
| 624 |
+
"loss": 0.1612,
|
| 625 |
+
"num_input_tokens_seen": 39424000,
|
| 626 |
+
"step": 38500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.975,
|
| 630 |
+
"grad_norm": 0.1407538652420044,
|
| 631 |
+
"learning_rate": 3.3750416666666665e-05,
|
| 632 |
+
"loss": 0.1336,
|
| 633 |
+
"num_input_tokens_seen": 39936000,
|
| 634 |
+
"step": 39000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.9875,
|
| 638 |
+
"grad_norm": 8.721837997436523,
|
| 639 |
+
"learning_rate": 3.3542083333333335e-05,
|
| 640 |
+
"loss": 0.1268,
|
| 641 |
+
"num_input_tokens_seen": 40448000,
|
| 642 |
+
"step": 39500
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.0,
|
| 646 |
+
"grad_norm": 0.15711814165115356,
|
| 647 |
+
"learning_rate": 3.333375e-05,
|
| 648 |
+
"loss": 0.1387,
|
| 649 |
+
"num_input_tokens_seen": 40960000,
|
| 650 |
+
"step": 40000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.0,
|
| 654 |
+
"eval_accuracy": 0.951525,
|
| 655 |
+
"eval_combined_score": 1.3493705490187269,
|
| 656 |
+
"eval_loss": 0.198301300406456,
|
| 657 |
+
"eval_runtime": 39.36,
|
| 658 |
+
"eval_samples_per_second": 2032.519,
|
| 659 |
+
"eval_steps_per_second": 254.065,
|
| 660 |
+
"num_input_tokens_seen": 40960000,
|
| 661 |
+
"step": 40000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.0125,
|
| 665 |
+
"grad_norm": 0.02203565090894699,
|
| 666 |
+
"learning_rate": 3.312541666666667e-05,
|
| 667 |
+
"loss": 0.1092,
|
| 668 |
+
"num_input_tokens_seen": 41472000,
|
| 669 |
+
"step": 40500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.025,
|
| 673 |
+
"grad_norm": 328.5529479980469,
|
| 674 |
+
"learning_rate": 3.291708333333334e-05,
|
| 675 |
+
"loss": 0.0844,
|
| 676 |
+
"num_input_tokens_seen": 41984000,
|
| 677 |
+
"step": 41000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.0375,
|
| 681 |
+
"grad_norm": 0.11391662806272507,
|
| 682 |
+
"learning_rate": 3.270875e-05,
|
| 683 |
+
"loss": 0.1115,
|
| 684 |
+
"num_input_tokens_seen": 42496000,
|
| 685 |
+
"step": 41500
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.05,
|
| 689 |
+
"grad_norm": 0.07919144630432129,
|
| 690 |
+
"learning_rate": 3.250041666666667e-05,
|
| 691 |
+
"loss": 0.0878,
|
| 692 |
+
"num_input_tokens_seen": 43008000,
|
| 693 |
+
"step": 42000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.0625,
|
| 697 |
+
"grad_norm": 0.029733452945947647,
|
| 698 |
+
"learning_rate": 3.229208333333333e-05,
|
| 699 |
+
"loss": 0.0914,
|
| 700 |
+
"num_input_tokens_seen": 43520000,
|
| 701 |
+
"step": 42500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 1.075,
|
| 705 |
+
"grad_norm": 0.277174711227417,
|
| 706 |
+
"learning_rate": 3.208375e-05,
|
| 707 |
+
"loss": 0.1028,
|
| 708 |
+
"num_input_tokens_seen": 44032000,
|
| 709 |
+
"step": 43000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0875,
|
| 713 |
+
"grad_norm": 0.11592718958854675,
|
| 714 |
+
"learning_rate": 3.1875416666666666e-05,
|
| 715 |
+
"loss": 0.1032,
|
| 716 |
+
"num_input_tokens_seen": 44544000,
|
| 717 |
+
"step": 43500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.1,
|
| 721 |
+
"grad_norm": 0.2565874755382538,
|
| 722 |
+
"learning_rate": 3.166708333333334e-05,
|
| 723 |
+
"loss": 0.0912,
|
| 724 |
+
"num_input_tokens_seen": 45056000,
|
| 725 |
+
"step": 44000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.1125,
|
| 729 |
+
"grad_norm": 0.03557795658707619,
|
| 730 |
+
"learning_rate": 3.145875e-05,
|
| 731 |
+
"loss": 0.0882,
|
| 732 |
+
"num_input_tokens_seen": 45568000,
|
| 733 |
+
"step": 44500
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.125,
|
| 737 |
+
"grad_norm": 4.72824764251709,
|
| 738 |
+
"learning_rate": 3.125041666666667e-05,
|
| 739 |
+
"loss": 0.0918,
|
| 740 |
+
"num_input_tokens_seen": 46080000,
|
| 741 |
+
"step": 45000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.1375,
|
| 745 |
+
"grad_norm": 0.10075237601995468,
|
| 746 |
+
"learning_rate": 3.1042083333333335e-05,
|
| 747 |
+
"loss": 0.1117,
|
| 748 |
+
"num_input_tokens_seen": 46592000,
|
| 749 |
+
"step": 45500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.15,
|
| 753 |
+
"grad_norm": 0.07608671486377716,
|
| 754 |
+
"learning_rate": 3.083375e-05,
|
| 755 |
+
"loss": 0.1383,
|
| 756 |
+
"num_input_tokens_seen": 47104000,
|
| 757 |
+
"step": 46000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.1625,
|
| 761 |
+
"grad_norm": 14.187911033630371,
|
| 762 |
+
"learning_rate": 3.062541666666667e-05,
|
| 763 |
+
"loss": 0.1062,
|
| 764 |
+
"num_input_tokens_seen": 47616000,
|
| 765 |
+
"step": 46500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.175,
|
| 769 |
+
"grad_norm": 0.0889461487531662,
|
| 770 |
+
"learning_rate": 3.0417083333333334e-05,
|
| 771 |
+
"loss": 0.1255,
|
| 772 |
+
"num_input_tokens_seen": 48128000,
|
| 773 |
+
"step": 47000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1875,
|
| 777 |
+
"grad_norm": 0.10722101479768753,
|
| 778 |
+
"learning_rate": 3.020875e-05,
|
| 779 |
+
"loss": 0.0987,
|
| 780 |
+
"num_input_tokens_seen": 48640000,
|
| 781 |
+
"step": 47500
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.2,
|
| 785 |
+
"grad_norm": 42.01722717285156,
|
| 786 |
+
"learning_rate": 3.000041666666667e-05,
|
| 787 |
+
"loss": 0.1047,
|
| 788 |
+
"num_input_tokens_seen": 49152000,
|
| 789 |
+
"step": 48000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.2125,
|
| 793 |
+
"grad_norm": 0.08817047625780106,
|
| 794 |
+
"learning_rate": 2.9792083333333336e-05,
|
| 795 |
+
"loss": 0.0931,
|
| 796 |
+
"num_input_tokens_seen": 49664000,
|
| 797 |
+
"step": 48500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.225,
|
| 801 |
+
"grad_norm": 0.058988332748413086,
|
| 802 |
+
"learning_rate": 2.958375e-05,
|
| 803 |
+
"loss": 0.1048,
|
| 804 |
+
"num_input_tokens_seen": 50176000,
|
| 805 |
+
"step": 49000
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.2375,
|
| 809 |
+
"grad_norm": 0.025500474497675896,
|
| 810 |
+
"learning_rate": 2.9375416666666667e-05,
|
| 811 |
+
"loss": 0.0845,
|
| 812 |
+
"num_input_tokens_seen": 50688000,
|
| 813 |
+
"step": 49500
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.25,
|
| 817 |
+
"grad_norm": 0.07621040940284729,
|
| 818 |
+
"learning_rate": 2.9167083333333334e-05,
|
| 819 |
+
"loss": 0.0893,
|
| 820 |
+
"num_input_tokens_seen": 51200000,
|
| 821 |
+
"step": 50000
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.2625,
|
| 825 |
+
"grad_norm": 0.14059029519557953,
|
| 826 |
+
"learning_rate": 2.895875e-05,
|
| 827 |
+
"loss": 0.0911,
|
| 828 |
+
"num_input_tokens_seen": 51712000,
|
| 829 |
+
"step": 50500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.275,
|
| 833 |
+
"grad_norm": 0.04900716617703438,
|
| 834 |
+
"learning_rate": 2.875041666666667e-05,
|
| 835 |
+
"loss": 0.0984,
|
| 836 |
+
"num_input_tokens_seen": 52224000,
|
| 837 |
+
"step": 51000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.2875,
|
| 841 |
+
"grad_norm": 0.0568259134888649,
|
| 842 |
+
"learning_rate": 2.8542083333333336e-05,
|
| 843 |
+
"loss": 0.0995,
|
| 844 |
+
"num_input_tokens_seen": 52736000,
|
| 845 |
+
"step": 51500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.3,
|
| 849 |
+
"grad_norm": 0.052453652024269104,
|
| 850 |
+
"learning_rate": 2.8333750000000003e-05,
|
| 851 |
+
"loss": 0.0875,
|
| 852 |
+
"num_input_tokens_seen": 53248000,
|
| 853 |
+
"step": 52000
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.3125,
|
| 857 |
+
"grad_norm": 0.05766982212662697,
|
| 858 |
+
"learning_rate": 2.812541666666667e-05,
|
| 859 |
+
"loss": 0.0772,
|
| 860 |
+
"num_input_tokens_seen": 53760000,
|
| 861 |
+
"step": 52500
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.325,
|
| 865 |
+
"grad_norm": 0.06809753179550171,
|
| 866 |
+
"learning_rate": 2.7917083333333334e-05,
|
| 867 |
+
"loss": 0.0849,
|
| 868 |
+
"num_input_tokens_seen": 54272000,
|
| 869 |
+
"step": 53000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.3375,
|
| 873 |
+
"grad_norm": 0.5180730223655701,
|
| 874 |
+
"learning_rate": 2.770875e-05,
|
| 875 |
+
"loss": 0.089,
|
| 876 |
+
"num_input_tokens_seen": 54784000,
|
| 877 |
+
"step": 53500
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.35,
|
| 881 |
+
"grad_norm": 12.439111709594727,
|
| 882 |
+
"learning_rate": 2.750041666666667e-05,
|
| 883 |
+
"loss": 0.0927,
|
| 884 |
+
"num_input_tokens_seen": 55296000,
|
| 885 |
+
"step": 54000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.3625,
|
| 889 |
+
"grad_norm": 0.12473966181278229,
|
| 890 |
+
"learning_rate": 2.7292083333333336e-05,
|
| 891 |
+
"loss": 0.1109,
|
| 892 |
+
"num_input_tokens_seen": 55808000,
|
| 893 |
+
"step": 54500
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 1.375,
|
| 897 |
+
"grad_norm": 1.5988309383392334,
|
| 898 |
+
"learning_rate": 2.7083750000000003e-05,
|
| 899 |
+
"loss": 0.0962,
|
| 900 |
+
"num_input_tokens_seen": 56320000,
|
| 901 |
+
"step": 55000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.3875,
|
| 905 |
+
"grad_norm": 0.09568974375724792,
|
| 906 |
+
"learning_rate": 2.687541666666667e-05,
|
| 907 |
+
"loss": 0.1041,
|
| 908 |
+
"num_input_tokens_seen": 56832000,
|
| 909 |
+
"step": 55500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.4,
|
| 913 |
+
"grad_norm": 105.98346710205078,
|
| 914 |
+
"learning_rate": 2.6667083333333338e-05,
|
| 915 |
+
"loss": 0.0895,
|
| 916 |
+
"num_input_tokens_seen": 57344000,
|
| 917 |
+
"step": 56000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.4125,
|
| 921 |
+
"grad_norm": 0.04284173250198364,
|
| 922 |
+
"learning_rate": 2.6458749999999998e-05,
|
| 923 |
+
"loss": 0.09,
|
| 924 |
+
"num_input_tokens_seen": 57856000,
|
| 925 |
+
"step": 56500
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.425,
|
| 929 |
+
"grad_norm": 0.06827585399150848,
|
| 930 |
+
"learning_rate": 2.6250416666666665e-05,
|
| 931 |
+
"loss": 0.1064,
|
| 932 |
+
"num_input_tokens_seen": 58368000,
|
| 933 |
+
"step": 57000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.4375,
|
| 937 |
+
"grad_norm": 0.10431079566478729,
|
| 938 |
+
"learning_rate": 2.6042083333333333e-05,
|
| 939 |
+
"loss": 0.1033,
|
| 940 |
+
"num_input_tokens_seen": 58880000,
|
| 941 |
+
"step": 57500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.45,
|
| 945 |
+
"grad_norm": 0.08796288073062897,
|
| 946 |
+
"learning_rate": 2.583375e-05,
|
| 947 |
+
"loss": 0.0781,
|
| 948 |
+
"num_input_tokens_seen": 59392000,
|
| 949 |
+
"step": 58000
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 1.4625,
|
| 953 |
+
"grad_norm": 1.883025884628296,
|
| 954 |
+
"learning_rate": 2.5625416666666667e-05,
|
| 955 |
+
"loss": 0.1001,
|
| 956 |
+
"num_input_tokens_seen": 59904000,
|
| 957 |
+
"step": 58500
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.475,
|
| 961 |
+
"grad_norm": 0.2901429533958435,
|
| 962 |
+
"learning_rate": 2.5417083333333334e-05,
|
| 963 |
+
"loss": 0.0965,
|
| 964 |
+
"num_input_tokens_seen": 60416000,
|
| 965 |
+
"step": 59000
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.4875,
|
| 969 |
+
"grad_norm": 0.05163797363638878,
|
| 970 |
+
"learning_rate": 2.520875e-05,
|
| 971 |
+
"loss": 0.1064,
|
| 972 |
+
"num_input_tokens_seen": 60928000,
|
| 973 |
+
"step": 59500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.5,
|
| 977 |
+
"grad_norm": 0.03811231628060341,
|
| 978 |
+
"learning_rate": 2.5000416666666672e-05,
|
| 979 |
+
"loss": 0.0865,
|
| 980 |
+
"num_input_tokens_seen": 61440000,
|
| 981 |
+
"step": 60000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.5125,
|
| 985 |
+
"grad_norm": 8.308381080627441,
|
| 986 |
+
"learning_rate": 2.4792083333333336e-05,
|
| 987 |
+
"loss": 0.093,
|
| 988 |
+
"num_input_tokens_seen": 61952000,
|
| 989 |
+
"step": 60500
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.525,
|
| 993 |
+
"grad_norm": 0.03729177638888359,
|
| 994 |
+
"learning_rate": 2.458375e-05,
|
| 995 |
+
"loss": 0.077,
|
| 996 |
+
"num_input_tokens_seen": 62464000,
|
| 997 |
+
"step": 61000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5375,
|
| 1001 |
+
"grad_norm": 5.803088188171387,
|
| 1002 |
+
"learning_rate": 2.4375416666666667e-05,
|
| 1003 |
+
"loss": 0.101,
|
| 1004 |
+
"num_input_tokens_seen": 62976000,
|
| 1005 |
+
"step": 61500
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.55,
|
| 1009 |
+
"grad_norm": 2.017042636871338,
|
| 1010 |
+
"learning_rate": 2.4167083333333334e-05,
|
| 1011 |
+
"loss": 0.0896,
|
| 1012 |
+
"num_input_tokens_seen": 63488000,
|
| 1013 |
+
"step": 62000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.5625,
|
| 1017 |
+
"grad_norm": 32.310630798339844,
|
| 1018 |
+
"learning_rate": 2.395875e-05,
|
| 1019 |
+
"loss": 0.1145,
|
| 1020 |
+
"num_input_tokens_seen": 64000000,
|
| 1021 |
+
"step": 62500
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.575,
|
| 1025 |
+
"grad_norm": 0.37863266468048096,
|
| 1026 |
+
"learning_rate": 2.3750416666666665e-05,
|
| 1027 |
+
"loss": 0.1017,
|
| 1028 |
+
"num_input_tokens_seen": 64512000,
|
| 1029 |
+
"step": 63000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.5875,
|
| 1033 |
+
"grad_norm": 0.05939273163676262,
|
| 1034 |
+
"learning_rate": 2.3542083333333333e-05,
|
| 1035 |
+
"loss": 0.0962,
|
| 1036 |
+
"num_input_tokens_seen": 65024000,
|
| 1037 |
+
"step": 63500
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.6,
|
| 1041 |
+
"grad_norm": 0.045398563146591187,
|
| 1042 |
+
"learning_rate": 2.333375e-05,
|
| 1043 |
+
"loss": 0.0895,
|
| 1044 |
+
"num_input_tokens_seen": 65536000,
|
| 1045 |
+
"step": 64000
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.6125,
|
| 1049 |
+
"grad_norm": 1.5717942714691162,
|
| 1050 |
+
"learning_rate": 2.3125416666666667e-05,
|
| 1051 |
+
"loss": 0.0788,
|
| 1052 |
+
"num_input_tokens_seen": 66048000,
|
| 1053 |
+
"step": 64500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.625,
|
| 1057 |
+
"grad_norm": 6.278552532196045,
|
| 1058 |
+
"learning_rate": 2.2917083333333334e-05,
|
| 1059 |
+
"loss": 0.0876,
|
| 1060 |
+
"num_input_tokens_seen": 66560000,
|
| 1061 |
+
"step": 65000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.6375,
|
| 1065 |
+
"grad_norm": 0.048090457916259766,
|
| 1066 |
+
"learning_rate": 2.2708750000000002e-05,
|
| 1067 |
+
"loss": 0.0709,
|
| 1068 |
+
"num_input_tokens_seen": 67072000,
|
| 1069 |
+
"step": 65500
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.65,
|
| 1073 |
+
"grad_norm": 0.5121225714683533,
|
| 1074 |
+
"learning_rate": 2.250041666666667e-05,
|
| 1075 |
+
"loss": 0.0906,
|
| 1076 |
+
"num_input_tokens_seen": 67584000,
|
| 1077 |
+
"step": 66000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.6625,
|
| 1081 |
+
"grad_norm": 0.04399065673351288,
|
| 1082 |
+
"learning_rate": 2.2292083333333336e-05,
|
| 1083 |
+
"loss": 0.097,
|
| 1084 |
+
"num_input_tokens_seen": 68096000,
|
| 1085 |
+
"step": 66500
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.675,
|
| 1089 |
+
"grad_norm": 0.051211412996053696,
|
| 1090 |
+
"learning_rate": 2.208375e-05,
|
| 1091 |
+
"loss": 0.0931,
|
| 1092 |
+
"num_input_tokens_seen": 68608000,
|
| 1093 |
+
"step": 67000
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.6875,
|
| 1097 |
+
"grad_norm": 58.19650650024414,
|
| 1098 |
+
"learning_rate": 2.1875416666666667e-05,
|
| 1099 |
+
"loss": 0.0794,
|
| 1100 |
+
"num_input_tokens_seen": 69120000,
|
| 1101 |
+
"step": 67500
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.7,
|
| 1105 |
+
"grad_norm": 0.07303386926651001,
|
| 1106 |
+
"learning_rate": 2.1667083333333335e-05,
|
| 1107 |
+
"loss": 0.1015,
|
| 1108 |
+
"num_input_tokens_seen": 69632000,
|
| 1109 |
+
"step": 68000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.7125,
|
| 1113 |
+
"grad_norm": 0.02853875607252121,
|
| 1114 |
+
"learning_rate": 2.145875e-05,
|
| 1115 |
+
"loss": 0.0684,
|
| 1116 |
+
"num_input_tokens_seen": 70144000,
|
| 1117 |
+
"step": 68500
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.725,
|
| 1121 |
+
"grad_norm": 0.06810135394334793,
|
| 1122 |
+
"learning_rate": 2.1250416666666666e-05,
|
| 1123 |
+
"loss": 0.101,
|
| 1124 |
+
"num_input_tokens_seen": 70656000,
|
| 1125 |
+
"step": 69000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.7375,
|
| 1129 |
+
"grad_norm": 0.019835174083709717,
|
| 1130 |
+
"learning_rate": 2.1042083333333333e-05,
|
| 1131 |
+
"loss": 0.0719,
|
| 1132 |
+
"num_input_tokens_seen": 71168000,
|
| 1133 |
+
"step": 69500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.75,
|
| 1137 |
+
"grad_norm": 0.07850214093923569,
|
| 1138 |
+
"learning_rate": 2.083375e-05,
|
| 1139 |
+
"loss": 0.0808,
|
| 1140 |
+
"num_input_tokens_seen": 71680000,
|
| 1141 |
+
"step": 70000
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.7625,
|
| 1145 |
+
"grad_norm": 0.050091035664081573,
|
| 1146 |
+
"learning_rate": 2.0625416666666667e-05,
|
| 1147 |
+
"loss": 0.0835,
|
| 1148 |
+
"num_input_tokens_seen": 72192000,
|
| 1149 |
+
"step": 70500
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.775,
|
| 1153 |
+
"grad_norm": 0.01498348731547594,
|
| 1154 |
+
"learning_rate": 2.0417083333333335e-05,
|
| 1155 |
+
"loss": 0.0918,
|
| 1156 |
+
"num_input_tokens_seen": 72704000,
|
| 1157 |
+
"step": 71000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.7875,
|
| 1161 |
+
"grad_norm": 0.034435465931892395,
|
| 1162 |
+
"learning_rate": 2.0208750000000002e-05,
|
| 1163 |
+
"loss": 0.0777,
|
| 1164 |
+
"num_input_tokens_seen": 73216000,
|
| 1165 |
+
"step": 71500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.8,
|
| 1169 |
+
"grad_norm": 0.045340586453676224,
|
| 1170 |
+
"learning_rate": 2.000041666666667e-05,
|
| 1171 |
+
"loss": 0.0894,
|
| 1172 |
+
"num_input_tokens_seen": 73728000,
|
| 1173 |
+
"step": 72000
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.8125,
|
| 1177 |
+
"grad_norm": 0.28705134987831116,
|
| 1178 |
+
"learning_rate": 1.9792083333333333e-05,
|
| 1179 |
+
"loss": 0.0741,
|
| 1180 |
+
"num_input_tokens_seen": 74240000,
|
| 1181 |
+
"step": 72500
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 1.825,
|
| 1185 |
+
"grad_norm": 155.12445068359375,
|
| 1186 |
+
"learning_rate": 1.958375e-05,
|
| 1187 |
+
"loss": 0.0813,
|
| 1188 |
+
"num_input_tokens_seen": 74752000,
|
| 1189 |
+
"step": 73000
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.8375,
|
| 1193 |
+
"grad_norm": 0.08065774291753769,
|
| 1194 |
+
"learning_rate": 1.9375416666666668e-05,
|
| 1195 |
+
"loss": 0.0819,
|
| 1196 |
+
"num_input_tokens_seen": 75264000,
|
| 1197 |
+
"step": 73500
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.85,
|
| 1201 |
+
"grad_norm": 0.40842482447624207,
|
| 1202 |
+
"learning_rate": 1.9167083333333335e-05,
|
| 1203 |
+
"loss": 0.0669,
|
| 1204 |
+
"num_input_tokens_seen": 75776000,
|
| 1205 |
+
"step": 74000
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.8625,
|
| 1209 |
+
"grad_norm": 0.09376771003007889,
|
| 1210 |
+
"learning_rate": 1.895875e-05,
|
| 1211 |
+
"loss": 0.0749,
|
| 1212 |
+
"num_input_tokens_seen": 76288000,
|
| 1213 |
+
"step": 74500
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.875,
|
| 1217 |
+
"grad_norm": 0.035654786974191666,
|
| 1218 |
+
"learning_rate": 1.8750416666666666e-05,
|
| 1219 |
+
"loss": 0.0757,
|
| 1220 |
+
"num_input_tokens_seen": 76800000,
|
| 1221 |
+
"step": 75000
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.8875,
|
| 1225 |
+
"grad_norm": 0.04763418436050415,
|
| 1226 |
+
"learning_rate": 1.8542083333333337e-05,
|
| 1227 |
+
"loss": 0.0652,
|
| 1228 |
+
"num_input_tokens_seen": 77312000,
|
| 1229 |
+
"step": 75500
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.9,
|
| 1233 |
+
"grad_norm": 0.04799911379814148,
|
| 1234 |
+
"learning_rate": 1.833375e-05,
|
| 1235 |
+
"loss": 0.0688,
|
| 1236 |
+
"num_input_tokens_seen": 77824000,
|
| 1237 |
+
"step": 76000
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 1.9125,
|
| 1241 |
+
"grad_norm": 0.22011104226112366,
|
| 1242 |
+
"learning_rate": 1.8125416666666668e-05,
|
| 1243 |
+
"loss": 0.0797,
|
| 1244 |
+
"num_input_tokens_seen": 78336000,
|
| 1245 |
+
"step": 76500
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.925,
|
| 1249 |
+
"grad_norm": 0.05009845644235611,
|
| 1250 |
+
"learning_rate": 1.7917083333333335e-05,
|
| 1251 |
+
"loss": 0.0542,
|
| 1252 |
+
"num_input_tokens_seen": 78848000,
|
| 1253 |
+
"step": 77000
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.9375,
|
| 1257 |
+
"grad_norm": 1.8440918922424316,
|
| 1258 |
+
"learning_rate": 1.7708750000000002e-05,
|
| 1259 |
+
"loss": 0.0773,
|
| 1260 |
+
"num_input_tokens_seen": 79360000,
|
| 1261 |
+
"step": 77500
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.95,
|
| 1265 |
+
"grad_norm": 0.025103362277150154,
|
| 1266 |
+
"learning_rate": 1.7500416666666666e-05,
|
| 1267 |
+
"loss": 0.0692,
|
| 1268 |
+
"num_input_tokens_seen": 79872000,
|
| 1269 |
+
"step": 78000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.9625,
|
| 1273 |
+
"grad_norm": 14.473067283630371,
|
| 1274 |
+
"learning_rate": 1.7292083333333333e-05,
|
| 1275 |
+
"loss": 0.0658,
|
| 1276 |
+
"num_input_tokens_seen": 80384000,
|
| 1277 |
+
"step": 78500
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.975,
|
| 1281 |
+
"grad_norm": 0.051201172173023224,
|
| 1282 |
+
"learning_rate": 1.708375e-05,
|
| 1283 |
+
"loss": 0.0648,
|
| 1284 |
+
"num_input_tokens_seen": 80896000,
|
| 1285 |
+
"step": 79000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.9875,
|
| 1289 |
+
"grad_norm": 0.05888315662741661,
|
| 1290 |
+
"learning_rate": 1.6875416666666668e-05,
|
| 1291 |
+
"loss": 0.0792,
|
| 1292 |
+
"num_input_tokens_seen": 81408000,
|
| 1293 |
+
"step": 79500
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.0,
|
| 1297 |
+
"grad_norm": 0.08364333212375641,
|
| 1298 |
+
"learning_rate": 1.666708333333333e-05,
|
| 1299 |
+
"loss": 0.0682,
|
| 1300 |
+
"num_input_tokens_seen": 81920000,
|
| 1301 |
+
"step": 80000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.0,
|
| 1305 |
+
"eval_accuracy": 0.9528,
|
| 1306 |
+
"eval_combined_score": 1.327030219983165,
|
| 1307 |
+
"eval_loss": 0.22639968991279602,
|
| 1308 |
+
"eval_runtime": 39.5018,
|
| 1309 |
+
"eval_samples_per_second": 2025.225,
|
| 1310 |
+
"eval_steps_per_second": 253.153,
|
| 1311 |
+
"num_input_tokens_seen": 81920000,
|
| 1312 |
+
"step": 80000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.0125,
|
| 1316 |
+
"grad_norm": 1.8050274848937988,
|
| 1317 |
+
"learning_rate": 1.645875e-05,
|
| 1318 |
+
"loss": 0.0508,
|
| 1319 |
+
"num_input_tokens_seen": 82432000,
|
| 1320 |
+
"step": 80500
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.025,
|
| 1324 |
+
"grad_norm": 0.02845793031156063,
|
| 1325 |
+
"learning_rate": 1.625041666666667e-05,
|
| 1326 |
+
"loss": 0.0525,
|
| 1327 |
+
"num_input_tokens_seen": 82944000,
|
| 1328 |
+
"step": 81000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 2.0375,
|
| 1332 |
+
"grad_norm": 0.025743141770362854,
|
| 1333 |
+
"learning_rate": 1.6042083333333337e-05,
|
| 1334 |
+
"loss": 0.0483,
|
| 1335 |
+
"num_input_tokens_seen": 83456000,
|
| 1336 |
+
"step": 81500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.05,
|
| 1340 |
+
"grad_norm": 8.399374008178711,
|
| 1341 |
+
"learning_rate": 1.583375e-05,
|
| 1342 |
+
"loss": 0.0652,
|
| 1343 |
+
"num_input_tokens_seen": 83968000,
|
| 1344 |
+
"step": 82000
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.0625,
|
| 1348 |
+
"grad_norm": 0.017835861071944237,
|
| 1349 |
+
"learning_rate": 1.5625416666666668e-05,
|
| 1350 |
+
"loss": 0.0482,
|
| 1351 |
+
"num_input_tokens_seen": 84480000,
|
| 1352 |
+
"step": 82500
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 2.075,
|
| 1356 |
+
"grad_norm": 0.06692575663328171,
|
| 1357 |
+
"learning_rate": 1.5417083333333335e-05,
|
| 1358 |
+
"loss": 0.0521,
|
| 1359 |
+
"num_input_tokens_seen": 84992000,
|
| 1360 |
+
"step": 83000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.0875,
|
| 1364 |
+
"grad_norm": 0.035685233771800995,
|
| 1365 |
+
"learning_rate": 1.5208749999999999e-05,
|
| 1366 |
+
"loss": 0.0582,
|
| 1367 |
+
"num_input_tokens_seen": 85504000,
|
| 1368 |
+
"step": 83500
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.1,
|
| 1372 |
+
"grad_norm": 0.13481773436069489,
|
| 1373 |
+
"learning_rate": 1.5000416666666666e-05,
|
| 1374 |
+
"loss": 0.0468,
|
| 1375 |
+
"num_input_tokens_seen": 86016000,
|
| 1376 |
+
"step": 84000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.1125,
|
| 1380 |
+
"grad_norm": 17.486289978027344,
|
| 1381 |
+
"learning_rate": 1.4792083333333334e-05,
|
| 1382 |
+
"loss": 0.0559,
|
| 1383 |
+
"num_input_tokens_seen": 86528000,
|
| 1384 |
+
"step": 84500
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 2.125,
|
| 1388 |
+
"grad_norm": 0.03201691806316376,
|
| 1389 |
+
"learning_rate": 1.458375e-05,
|
| 1390 |
+
"loss": 0.0425,
|
| 1391 |
+
"num_input_tokens_seen": 87040000,
|
| 1392 |
+
"step": 85000
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.1375,
|
| 1396 |
+
"grad_norm": 0.021227147430181503,
|
| 1397 |
+
"learning_rate": 1.4375416666666666e-05,
|
| 1398 |
+
"loss": 0.05,
|
| 1399 |
+
"num_input_tokens_seen": 87552000,
|
| 1400 |
+
"step": 85500
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 2.15,
|
| 1404 |
+
"grad_norm": 0.040053412318229675,
|
| 1405 |
+
"learning_rate": 1.4167083333333334e-05,
|
| 1406 |
+
"loss": 0.048,
|
| 1407 |
+
"num_input_tokens_seen": 88064000,
|
| 1408 |
+
"step": 86000
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 2.1625,
|
| 1412 |
+
"grad_norm": 0.01835712045431137,
|
| 1413 |
+
"learning_rate": 1.395875e-05,
|
| 1414 |
+
"loss": 0.038,
|
| 1415 |
+
"num_input_tokens_seen": 88576000,
|
| 1416 |
+
"step": 86500
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.175,
|
| 1420 |
+
"grad_norm": 0.03529110550880432,
|
| 1421 |
+
"learning_rate": 1.3750416666666668e-05,
|
| 1422 |
+
"loss": 0.051,
|
| 1423 |
+
"num_input_tokens_seen": 89088000,
|
| 1424 |
+
"step": 87000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.1875,
|
| 1428 |
+
"grad_norm": 97.47898864746094,
|
| 1429 |
+
"learning_rate": 1.3542083333333334e-05,
|
| 1430 |
+
"loss": 0.0373,
|
| 1431 |
+
"num_input_tokens_seen": 89600000,
|
| 1432 |
+
"step": 87500
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.2,
|
| 1436 |
+
"grad_norm": 0.014346601441502571,
|
| 1437 |
+
"learning_rate": 1.3333750000000001e-05,
|
| 1438 |
+
"loss": 0.0557,
|
| 1439 |
+
"num_input_tokens_seen": 90112000,
|
| 1440 |
+
"step": 88000
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 2.2125,
|
| 1444 |
+
"grad_norm": 0.01878521591424942,
|
| 1445 |
+
"learning_rate": 1.3125416666666668e-05,
|
| 1446 |
+
"loss": 0.0526,
|
| 1447 |
+
"num_input_tokens_seen": 90624000,
|
| 1448 |
+
"step": 88500
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 2.225,
|
| 1452 |
+
"grad_norm": 0.04132438451051712,
|
| 1453 |
+
"learning_rate": 1.2917083333333335e-05,
|
| 1454 |
+
"loss": 0.0464,
|
| 1455 |
+
"num_input_tokens_seen": 91136000,
|
| 1456 |
+
"step": 89000
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.2375,
|
| 1460 |
+
"grad_norm": 0.02642699144780636,
|
| 1461 |
+
"learning_rate": 1.270875e-05,
|
| 1462 |
+
"loss": 0.0464,
|
| 1463 |
+
"num_input_tokens_seen": 91648000,
|
| 1464 |
+
"step": 89500
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.25,
|
| 1468 |
+
"grad_norm": 877.631591796875,
|
| 1469 |
+
"learning_rate": 1.2500416666666666e-05,
|
| 1470 |
+
"loss": 0.0374,
|
| 1471 |
+
"num_input_tokens_seen": 92160000,
|
| 1472 |
+
"step": 90000
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.2625,
|
| 1476 |
+
"grad_norm": 0.4528743326663971,
|
| 1477 |
+
"learning_rate": 1.2292083333333334e-05,
|
| 1478 |
+
"loss": 0.059,
|
| 1479 |
+
"num_input_tokens_seen": 92672000,
|
| 1480 |
+
"step": 90500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.275,
|
| 1484 |
+
"grad_norm": 0.1183973178267479,
|
| 1485 |
+
"learning_rate": 1.2083750000000001e-05,
|
| 1486 |
+
"loss": 0.0505,
|
| 1487 |
+
"num_input_tokens_seen": 93184000,
|
| 1488 |
+
"step": 91000
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.2875,
|
| 1492 |
+
"grad_norm": 0.04196188971400261,
|
| 1493 |
+
"learning_rate": 1.1875416666666667e-05,
|
| 1494 |
+
"loss": 0.0517,
|
| 1495 |
+
"num_input_tokens_seen": 93696000,
|
| 1496 |
+
"step": 91500
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 2.3,
|
| 1500 |
+
"grad_norm": 0.03194092586636543,
|
| 1501 |
+
"learning_rate": 1.1667083333333334e-05,
|
| 1502 |
+
"loss": 0.0511,
|
| 1503 |
+
"num_input_tokens_seen": 94208000,
|
| 1504 |
+
"step": 92000
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 2.3125,
|
| 1508 |
+
"grad_norm": 0.0184203889220953,
|
| 1509 |
+
"learning_rate": 1.145875e-05,
|
| 1510 |
+
"loss": 0.0501,
|
| 1511 |
+
"num_input_tokens_seen": 94720000,
|
| 1512 |
+
"step": 92500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.325,
|
| 1516 |
+
"grad_norm": 0.053758785128593445,
|
| 1517 |
+
"learning_rate": 1.1250416666666667e-05,
|
| 1518 |
+
"loss": 0.0412,
|
| 1519 |
+
"num_input_tokens_seen": 95232000,
|
| 1520 |
+
"step": 93000
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 2.3375,
|
| 1524 |
+
"grad_norm": 0.036872394382953644,
|
| 1525 |
+
"learning_rate": 1.1042083333333334e-05,
|
| 1526 |
+
"loss": 0.0418,
|
| 1527 |
+
"num_input_tokens_seen": 95744000,
|
| 1528 |
+
"step": 93500
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.35,
|
| 1532 |
+
"grad_norm": 0.014922083355486393,
|
| 1533 |
+
"learning_rate": 1.0833750000000001e-05,
|
| 1534 |
+
"loss": 0.0507,
|
| 1535 |
+
"num_input_tokens_seen": 96256000,
|
| 1536 |
+
"step": 94000
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.3625,
|
| 1540 |
+
"grad_norm": 0.020171664655208588,
|
| 1541 |
+
"learning_rate": 1.0625416666666667e-05,
|
| 1542 |
+
"loss": 0.0444,
|
| 1543 |
+
"num_input_tokens_seen": 96768000,
|
| 1544 |
+
"step": 94500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.375,
|
| 1548 |
+
"grad_norm": 1.7357385158538818,
|
| 1549 |
+
"learning_rate": 1.0417083333333334e-05,
|
| 1550 |
+
"loss": 0.0545,
|
| 1551 |
+
"num_input_tokens_seen": 97280000,
|
| 1552 |
+
"step": 95000
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 2.3875,
|
| 1556 |
+
"grad_norm": 0.023304857313632965,
|
| 1557 |
+
"learning_rate": 1.020875e-05,
|
| 1558 |
+
"loss": 0.0515,
|
| 1559 |
+
"num_input_tokens_seen": 97792000,
|
| 1560 |
+
"step": 95500
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 2.4,
|
| 1564 |
+
"grad_norm": 0.01939631998538971,
|
| 1565 |
+
"learning_rate": 1.0000416666666668e-05,
|
| 1566 |
+
"loss": 0.0495,
|
| 1567 |
+
"num_input_tokens_seen": 98304000,
|
| 1568 |
+
"step": 96000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 2.4125,
|
| 1572 |
+
"grad_norm": 0.019845569506287575,
|
| 1573 |
+
"learning_rate": 9.792083333333334e-06,
|
| 1574 |
+
"loss": 0.0411,
|
| 1575 |
+
"num_input_tokens_seen": 98816000,
|
| 1576 |
+
"step": 96500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 2.425,
|
| 1580 |
+
"grad_norm": 0.014959324151277542,
|
| 1581 |
+
"learning_rate": 9.583750000000001e-06,
|
| 1582 |
+
"loss": 0.0342,
|
| 1583 |
+
"num_input_tokens_seen": 99328000,
|
| 1584 |
+
"step": 97000
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.4375,
|
| 1588 |
+
"grad_norm": 0.01649474911391735,
|
| 1589 |
+
"learning_rate": 9.375416666666667e-06,
|
| 1590 |
+
"loss": 0.0472,
|
| 1591 |
+
"num_input_tokens_seen": 99840000,
|
| 1592 |
+
"step": 97500
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.45,
|
| 1596 |
+
"grad_norm": 0.031929146498441696,
|
| 1597 |
+
"learning_rate": 9.167083333333332e-06,
|
| 1598 |
+
"loss": 0.0384,
|
| 1599 |
+
"num_input_tokens_seen": 100352000,
|
| 1600 |
+
"step": 98000
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.4625,
|
| 1604 |
+
"grad_norm": 0.10980285704135895,
|
| 1605 |
+
"learning_rate": 8.958750000000001e-06,
|
| 1606 |
+
"loss": 0.0513,
|
| 1607 |
+
"num_input_tokens_seen": 100864000,
|
| 1608 |
+
"step": 98500
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.475,
|
| 1612 |
+
"grad_norm": 0.020933426916599274,
|
| 1613 |
+
"learning_rate": 8.750416666666667e-06,
|
| 1614 |
+
"loss": 0.0478,
|
| 1615 |
+
"num_input_tokens_seen": 101376000,
|
| 1616 |
+
"step": 99000
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 2.4875,
|
| 1620 |
+
"grad_norm": 0.017404716461896896,
|
| 1621 |
+
"learning_rate": 8.542083333333334e-06,
|
| 1622 |
+
"loss": 0.039,
|
| 1623 |
+
"num_input_tokens_seen": 101888000,
|
| 1624 |
+
"step": 99500
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 2.5,
|
| 1628 |
+
"grad_norm": 0.11211936920881271,
|
| 1629 |
+
"learning_rate": 8.33375e-06,
|
| 1630 |
+
"loss": 0.0473,
|
| 1631 |
+
"num_input_tokens_seen": 102400000,
|
| 1632 |
+
"step": 100000
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 2.5125,
|
| 1636 |
+
"grad_norm": 0.023433908820152283,
|
| 1637 |
+
"learning_rate": 8.125416666666667e-06,
|
| 1638 |
+
"loss": 0.0417,
|
| 1639 |
+
"num_input_tokens_seen": 102912000,
|
| 1640 |
+
"step": 100500
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.525,
|
| 1644 |
+
"grad_norm": 0.011504637077450752,
|
| 1645 |
+
"learning_rate": 7.917083333333334e-06,
|
| 1646 |
+
"loss": 0.0396,
|
| 1647 |
+
"num_input_tokens_seen": 103424000,
|
| 1648 |
+
"step": 101000
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.5375,
|
| 1652 |
+
"grad_norm": 0.012843768112361431,
|
| 1653 |
+
"learning_rate": 7.708750000000001e-06,
|
| 1654 |
+
"loss": 0.0475,
|
| 1655 |
+
"num_input_tokens_seen": 103936000,
|
| 1656 |
+
"step": 101500
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.55,
|
| 1660 |
+
"grad_norm": 0.020524220541119576,
|
| 1661 |
+
"learning_rate": 7.500416666666667e-06,
|
| 1662 |
+
"loss": 0.0472,
|
| 1663 |
+
"num_input_tokens_seen": 104448000,
|
| 1664 |
+
"step": 102000
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.5625,
|
| 1668 |
+
"grad_norm": 0.01861303672194481,
|
| 1669 |
+
"learning_rate": 7.292083333333334e-06,
|
| 1670 |
+
"loss": 0.0294,
|
| 1671 |
+
"num_input_tokens_seen": 104960000,
|
| 1672 |
+
"step": 102500
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 2.575,
|
| 1676 |
+
"grad_norm": 0.021343663334846497,
|
| 1677 |
+
"learning_rate": 7.08375e-06,
|
| 1678 |
+
"loss": 0.0376,
|
| 1679 |
+
"num_input_tokens_seen": 105472000,
|
| 1680 |
+
"step": 103000
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 2.5875,
|
| 1684 |
+
"grad_norm": 0.8902124166488647,
|
| 1685 |
+
"learning_rate": 6.875416666666668e-06,
|
| 1686 |
+
"loss": 0.0456,
|
| 1687 |
+
"num_input_tokens_seen": 105984000,
|
| 1688 |
+
"step": 103500
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 2.6,
|
| 1692 |
+
"grad_norm": 0.06912536174058914,
|
| 1693 |
+
"learning_rate": 6.667083333333333e-06,
|
| 1694 |
+
"loss": 0.0365,
|
| 1695 |
+
"num_input_tokens_seen": 106496000,
|
| 1696 |
+
"step": 104000
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.6125,
|
| 1700 |
+
"grad_norm": 0.17968295514583588,
|
| 1701 |
+
"learning_rate": 6.458750000000001e-06,
|
| 1702 |
+
"loss": 0.0372,
|
| 1703 |
+
"num_input_tokens_seen": 107008000,
|
| 1704 |
+
"step": 104500
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.625,
|
| 1708 |
+
"grad_norm": 0.01591988280415535,
|
| 1709 |
+
"learning_rate": 6.250416666666667e-06,
|
| 1710 |
+
"loss": 0.0334,
|
| 1711 |
+
"num_input_tokens_seen": 107520000,
|
| 1712 |
+
"step": 105000
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 2.6375,
|
| 1716 |
+
"grad_norm": 0.015928415581583977,
|
| 1717 |
+
"learning_rate": 6.0420833333333334e-06,
|
| 1718 |
+
"loss": 0.0425,
|
| 1719 |
+
"num_input_tokens_seen": 108032000,
|
| 1720 |
+
"step": 105500
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.65,
|
| 1724 |
+
"grad_norm": 0.04025963693857193,
|
| 1725 |
+
"learning_rate": 5.833750000000001e-06,
|
| 1726 |
+
"loss": 0.0371,
|
| 1727 |
+
"num_input_tokens_seen": 108544000,
|
| 1728 |
+
"step": 106000
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 2.6625,
|
| 1732 |
+
"grad_norm": 0.07384547591209412,
|
| 1733 |
+
"learning_rate": 5.625416666666667e-06,
|
| 1734 |
+
"loss": 0.043,
|
| 1735 |
+
"num_input_tokens_seen": 109056000,
|
| 1736 |
+
"step": 106500
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 2.675,
|
| 1740 |
+
"grad_norm": 0.0424518883228302,
|
| 1741 |
+
"learning_rate": 5.4170833333333335e-06,
|
| 1742 |
+
"loss": 0.0349,
|
| 1743 |
+
"num_input_tokens_seen": 109568000,
|
| 1744 |
+
"step": 107000
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 2.6875,
|
| 1748 |
+
"grad_norm": 0.01949002780020237,
|
| 1749 |
+
"learning_rate": 5.208750000000001e-06,
|
| 1750 |
+
"loss": 0.04,
|
| 1751 |
+
"num_input_tokens_seen": 110080000,
|
| 1752 |
+
"step": 107500
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.7,
|
| 1756 |
+
"grad_norm": 0.011860487051308155,
|
| 1757 |
+
"learning_rate": 5.000416666666667e-06,
|
| 1758 |
+
"loss": 0.0274,
|
| 1759 |
+
"num_input_tokens_seen": 110592000,
|
| 1760 |
+
"step": 108000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.7125,
|
| 1764 |
+
"grad_norm": 0.010354108177125454,
|
| 1765 |
+
"learning_rate": 4.7920833333333335e-06,
|
| 1766 |
+
"loss": 0.0305,
|
| 1767 |
+
"num_input_tokens_seen": 111104000,
|
| 1768 |
+
"step": 108500
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.725,
|
| 1772 |
+
"grad_norm": 13.753798484802246,
|
| 1773 |
+
"learning_rate": 4.583750000000001e-06,
|
| 1774 |
+
"loss": 0.0446,
|
| 1775 |
+
"num_input_tokens_seen": 111616000,
|
| 1776 |
+
"step": 109000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 2.7375,
|
| 1780 |
+
"grad_norm": 0.017097918316721916,
|
| 1781 |
+
"learning_rate": 4.375416666666666e-06,
|
| 1782 |
+
"loss": 0.0398,
|
| 1783 |
+
"num_input_tokens_seen": 112128000,
|
| 1784 |
+
"step": 109500
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 2.75,
|
| 1788 |
+
"grad_norm": 0.01976764015853405,
|
| 1789 |
+
"learning_rate": 4.167083333333334e-06,
|
| 1790 |
+
"loss": 0.0318,
|
| 1791 |
+
"num_input_tokens_seen": 112640000,
|
| 1792 |
+
"step": 110000
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 2.7625,
|
| 1796 |
+
"grad_norm": 6.2214531898498535,
|
| 1797 |
+
"learning_rate": 3.95875e-06,
|
| 1798 |
+
"loss": 0.0424,
|
| 1799 |
+
"num_input_tokens_seen": 113152000,
|
| 1800 |
+
"step": 110500
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 2.775,
|
| 1804 |
+
"grad_norm": 0.007995002903044224,
|
| 1805 |
+
"learning_rate": 3.750416666666667e-06,
|
| 1806 |
+
"loss": 0.0442,
|
| 1807 |
+
"num_input_tokens_seen": 113664000,
|
| 1808 |
+
"step": 111000
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.7875,
|
| 1812 |
+
"grad_norm": 0.05575885996222496,
|
| 1813 |
+
"learning_rate": 3.5420833333333332e-06,
|
| 1814 |
+
"loss": 0.037,
|
| 1815 |
+
"num_input_tokens_seen": 114176000,
|
| 1816 |
+
"step": 111500
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.8,
|
| 1820 |
+
"grad_norm": 0.1336035579442978,
|
| 1821 |
+
"learning_rate": 3.33375e-06,
|
| 1822 |
+
"loss": 0.0385,
|
| 1823 |
+
"num_input_tokens_seen": 114688000,
|
| 1824 |
+
"step": 112000
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.8125,
|
| 1828 |
+
"grad_norm": 0.019037237390875816,
|
| 1829 |
+
"learning_rate": 3.125416666666667e-06,
|
| 1830 |
+
"loss": 0.0326,
|
| 1831 |
+
"num_input_tokens_seen": 115200000,
|
| 1832 |
+
"step": 112500
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 2.825,
|
| 1836 |
+
"grad_norm": 0.00875825248658657,
|
| 1837 |
+
"learning_rate": 2.9170833333333333e-06,
|
| 1838 |
+
"loss": 0.0277,
|
| 1839 |
+
"num_input_tokens_seen": 115712000,
|
| 1840 |
+
"step": 113000
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 2.8375,
|
| 1844 |
+
"grad_norm": 0.052571795880794525,
|
| 1845 |
+
"learning_rate": 2.70875e-06,
|
| 1846 |
+
"loss": 0.037,
|
| 1847 |
+
"num_input_tokens_seen": 116224000,
|
| 1848 |
+
"step": 113500
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 2.85,
|
| 1852 |
+
"grad_norm": 0.019845254719257355,
|
| 1853 |
+
"learning_rate": 2.500416666666667e-06,
|
| 1854 |
+
"loss": 0.0445,
|
| 1855 |
+
"num_input_tokens_seen": 116736000,
|
| 1856 |
+
"step": 114000
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 2.8625,
|
| 1860 |
+
"grad_norm": 0.01046211551874876,
|
| 1861 |
+
"learning_rate": 2.2920833333333338e-06,
|
| 1862 |
+
"loss": 0.0294,
|
| 1863 |
+
"num_input_tokens_seen": 117248000,
|
| 1864 |
+
"step": 114500
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.875,
|
| 1868 |
+
"grad_norm": 0.012272953987121582,
|
| 1869 |
+
"learning_rate": 2.0837499999999997e-06,
|
| 1870 |
+
"loss": 0.0396,
|
| 1871 |
+
"num_input_tokens_seen": 117760000,
|
| 1872 |
+
"step": 115000
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.8875,
|
| 1876 |
+
"grad_norm": 0.022472262382507324,
|
| 1877 |
+
"learning_rate": 1.8754166666666666e-06,
|
| 1878 |
+
"loss": 0.047,
|
| 1879 |
+
"num_input_tokens_seen": 118272000,
|
| 1880 |
+
"step": 115500
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 2.9,
|
| 1884 |
+
"grad_norm": 0.07120255380868912,
|
| 1885 |
+
"learning_rate": 1.6670833333333334e-06,
|
| 1886 |
+
"loss": 0.0437,
|
| 1887 |
+
"num_input_tokens_seen": 118784000,
|
| 1888 |
+
"step": 116000
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.9125,
|
| 1892 |
+
"grad_norm": 0.060723673552274704,
|
| 1893 |
+
"learning_rate": 1.45875e-06,
|
| 1894 |
+
"loss": 0.035,
|
| 1895 |
+
"num_input_tokens_seen": 119296000,
|
| 1896 |
+
"step": 116500
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 2.925,
|
| 1900 |
+
"grad_norm": 0.012350406497716904,
|
| 1901 |
+
"learning_rate": 1.2504166666666668e-06,
|
| 1902 |
+
"loss": 0.03,
|
| 1903 |
+
"num_input_tokens_seen": 119808000,
|
| 1904 |
+
"step": 117000
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 2.9375,
|
| 1908 |
+
"grad_norm": 0.18025244772434235,
|
| 1909 |
+
"learning_rate": 1.0420833333333334e-06,
|
| 1910 |
+
"loss": 0.0306,
|
| 1911 |
+
"num_input_tokens_seen": 120320000,
|
| 1912 |
+
"step": 117500
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 2.95,
|
| 1916 |
+
"grad_norm": 0.007316856179386377,
|
| 1917 |
+
"learning_rate": 8.3375e-07,
|
| 1918 |
+
"loss": 0.0328,
|
| 1919 |
+
"num_input_tokens_seen": 120832000,
|
| 1920 |
+
"step": 118000
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.9625,
|
| 1924 |
+
"grad_norm": 0.06496240198612213,
|
| 1925 |
+
"learning_rate": 6.254166666666667e-07,
|
| 1926 |
+
"loss": 0.039,
|
| 1927 |
+
"num_input_tokens_seen": 121344000,
|
| 1928 |
+
"step": 118500
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.975,
|
| 1932 |
+
"grad_norm": 0.0057182470336556435,
|
| 1933 |
+
"learning_rate": 4.170833333333334e-07,
|
| 1934 |
+
"loss": 0.0367,
|
| 1935 |
+
"num_input_tokens_seen": 121856000,
|
| 1936 |
+
"step": 119000
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.9875,
|
| 1940 |
+
"grad_norm": 0.017466630786657333,
|
| 1941 |
+
"learning_rate": 2.0875e-07,
|
| 1942 |
+
"loss": 0.0381,
|
| 1943 |
+
"num_input_tokens_seen": 122368000,
|
| 1944 |
+
"step": 119500
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 3.0,
|
| 1948 |
+
"grad_norm": 0.013719202019274235,
|
| 1949 |
+
"learning_rate": 4.1666666666666673e-10,
|
| 1950 |
+
"loss": 0.0424,
|
| 1951 |
+
"num_input_tokens_seen": 122880000,
|
| 1952 |
+
"step": 120000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 3.0,
|
| 1956 |
+
"eval_accuracy": 0.955225,
|
| 1957 |
+
"eval_combined_score": 1.2845397902488602,
|
| 1958 |
+
"eval_loss": 0.2597787082195282,
|
| 1959 |
+
"eval_runtime": 39.5285,
|
| 1960 |
+
"eval_samples_per_second": 2023.856,
|
| 1961 |
+
"eval_steps_per_second": 252.982,
|
| 1962 |
+
"num_input_tokens_seen": 122880000,
|
| 1963 |
+
"step": 120000
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 3.0,
|
| 1967 |
+
"num_input_tokens_seen": 122880000,
|
| 1968 |
+
"step": 120000,
|
| 1969 |
+
"total_flos": 1.580945522688e+16,
|
| 1970 |
+
"train_loss": 0.10143799341519674,
|
| 1971 |
+
"train_runtime": 4258.2582,
|
| 1972 |
+
"train_samples_per_second": 225.444,
|
| 1973 |
+
"train_steps_per_second": 28.181,
|
| 1974 |
+
"train_tokens_per_second": 28856.869
|
| 1975 |
+
}
|
| 1976 |
+
],
|
| 1977 |
+
"logging_steps": 500,
|
| 1978 |
+
"max_steps": 120000,
|
| 1979 |
+
"num_input_tokens_seen": 122880000,
|
| 1980 |
+
"num_train_epochs": 3,
|
| 1981 |
+
"save_steps": 500,
|
| 1982 |
+
"stateful_callbacks": {
|
| 1983 |
+
"TrainerControl": {
|
| 1984 |
+
"args": {
|
| 1985 |
+
"should_epoch_stop": false,
|
| 1986 |
+
"should_evaluate": false,
|
| 1987 |
+
"should_log": false,
|
| 1988 |
+
"should_save": true,
|
| 1989 |
+
"should_training_stop": true
|
| 1990 |
+
},
|
| 1991 |
+
"attributes": {}
|
| 1992 |
+
}
|
| 1993 |
+
},
|
| 1994 |
+
"total_flos": 1.580945522688e+16,
|
| 1995 |
+
"train_batch_size": 8,
|
| 1996 |
+
"trial_name": null,
|
| 1997 |
+
"trial_params": null
|
| 1998 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46d1b2953991d8ef95c15025aae629bf2e97252ca61ea56394fc14a438d43412
|
| 3 |
+
size 5496
|