Uploading model
Browse files- all_results.json +8 -0
- config.json +57 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- train_results.json +8 -0
- trainer_state.json +827 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.0681625740050432e+20,
|
| 4 |
+
"train_loss": 1.8866207526312935,
|
| 5 |
+
"train_runtime": 25047.9369,
|
| 6 |
+
"train_samples_per_second": 7.186,
|
| 7 |
+
"train_steps_per_second": 0.449
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BlipForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_text_hidden_size": 256,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"initializer_range": 0.02,
|
| 8 |
+
"label_smoothing": 0.0,
|
| 9 |
+
"logit_scale_init_value": 2.6592,
|
| 10 |
+
"model_type": "blip",
|
| 11 |
+
"projection_dim": 512,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"_attn_implementation_autoset": true,
|
| 14 |
+
"attention_probs_dropout_prob": 0.0,
|
| 15 |
+
"encoder_hidden_size": 768,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"initializer_factor": 1.0,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label_smoothing": 0.0,
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_length": 70,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"min_length": 5,
|
| 27 |
+
"model_type": "blip_text_model",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_beams": 3,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"projection_dim": 768,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30524
|
| 35 |
+
},
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.51.3",
|
| 38 |
+
"vision_config": {
|
| 39 |
+
"_attn_implementation_autoset": true,
|
| 40 |
+
"attention_dropout": 0.0,
|
| 41 |
+
"dropout": 0.0,
|
| 42 |
+
"hidden_act": "gelu",
|
| 43 |
+
"hidden_size": 768,
|
| 44 |
+
"image_size": 384,
|
| 45 |
+
"initializer_factor": 1.0,
|
| 46 |
+
"initializer_range": 0.02,
|
| 47 |
+
"intermediate_size": 3072,
|
| 48 |
+
"layer_norm_eps": 1e-05,
|
| 49 |
+
"model_type": "blip_vision_model",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_channels": 3,
|
| 52 |
+
"num_hidden_layers": 12,
|
| 53 |
+
"patch_size": 16,
|
| 54 |
+
"projection_dim": 512,
|
| 55 |
+
"torch_dtype": "float32"
|
| 56 |
+
}
|
| 57 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 30522,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ab027c7590ae19d7f5dc53e552ee959c2fb31b3e872e6f7864bb67cc17cab78
|
| 3 |
+
size 989717056
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "BlipImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"processor_class": "BlipProcessor",
|
| 18 |
+
"resample": 3,
|
| 19 |
+
"rescale_factor": 0.00392156862745098,
|
| 20 |
+
"size": {
|
| 21 |
+
"height": 384,
|
| 22 |
+
"width": 384
|
| 23 |
+
}
|
| 24 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_input_names": [
|
| 51 |
+
"input_ids",
|
| 52 |
+
"attention_mask"
|
| 53 |
+
],
|
| 54 |
+
"model_max_length": 512,
|
| 55 |
+
"never_split": null,
|
| 56 |
+
"pad_token": "[PAD]",
|
| 57 |
+
"processor_class": "BlipProcessor",
|
| 58 |
+
"sep_token": "[SEP]",
|
| 59 |
+
"strip_accents": null,
|
| 60 |
+
"tokenize_chinese_chars": true,
|
| 61 |
+
"tokenizer_class": "BertTokenizer",
|
| 62 |
+
"unk_token": "[UNK]"
|
| 63 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.0681625740050432e+20,
|
| 4 |
+
"train_loss": 1.8866207526312935,
|
| 5 |
+
"train_runtime": 25047.9369,
|
| 6 |
+
"train_samples_per_second": 7.186,
|
| 7 |
+
"train_steps_per_second": 0.449
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,827 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 11250,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02666666666666667,
|
| 14 |
+
"grad_norm": 4.86626672744751,
|
| 15 |
+
"learning_rate": 8.533333333333334e-07,
|
| 16 |
+
"loss": 8.0208,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05333333333333334,
|
| 21 |
+
"grad_norm": 3.3916521072387695,
|
| 22 |
+
"learning_rate": 1.7422222222222224e-06,
|
| 23 |
+
"loss": 5.8171,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08,
|
| 28 |
+
"grad_norm": 3.5112016201019287,
|
| 29 |
+
"learning_rate": 2.6311111111111115e-06,
|
| 30 |
+
"loss": 4.7527,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.10666666666666667,
|
| 35 |
+
"grad_norm": 3.508920669555664,
|
| 36 |
+
"learning_rate": 3.52e-06,
|
| 37 |
+
"loss": 4.0662,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.13333333333333333,
|
| 42 |
+
"grad_norm": 4.699676513671875,
|
| 43 |
+
"learning_rate": 4.408888888888889e-06,
|
| 44 |
+
"loss": 3.6461,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"grad_norm": 4.627090930938721,
|
| 50 |
+
"learning_rate": 5.297777777777778e-06,
|
| 51 |
+
"loss": 3.3864,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.18666666666666668,
|
| 56 |
+
"grad_norm": 4.664205074310303,
|
| 57 |
+
"learning_rate": 6.186666666666668e-06,
|
| 58 |
+
"loss": 3.1795,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.21333333333333335,
|
| 63 |
+
"grad_norm": 4.104228973388672,
|
| 64 |
+
"learning_rate": 7.0755555555555565e-06,
|
| 65 |
+
"loss": 3.0256,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.24,
|
| 70 |
+
"grad_norm": 3.472336530685425,
|
| 71 |
+
"learning_rate": 7.964444444444445e-06,
|
| 72 |
+
"loss": 2.9146,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.26666666666666666,
|
| 77 |
+
"grad_norm": 4.164829254150391,
|
| 78 |
+
"learning_rate": 8.853333333333334e-06,
|
| 79 |
+
"loss": 2.7903,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.29333333333333333,
|
| 84 |
+
"grad_norm": 3.6888585090637207,
|
| 85 |
+
"learning_rate": 9.742222222222222e-06,
|
| 86 |
+
"loss": 2.7095,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.32,
|
| 91 |
+
"grad_norm": 3.9901719093322754,
|
| 92 |
+
"learning_rate": 9.929876543209878e-06,
|
| 93 |
+
"loss": 2.6091,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3466666666666667,
|
| 98 |
+
"grad_norm": 4.848642826080322,
|
| 99 |
+
"learning_rate": 9.8320987654321e-06,
|
| 100 |
+
"loss": 2.525,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.37333333333333335,
|
| 105 |
+
"grad_norm": 3.7277579307556152,
|
| 106 |
+
"learning_rate": 9.733333333333334e-06,
|
| 107 |
+
"loss": 2.474,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4,
|
| 112 |
+
"grad_norm": 5.541881084442139,
|
| 113 |
+
"learning_rate": 9.634567901234568e-06,
|
| 114 |
+
"loss": 2.4034,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4266666666666667,
|
| 119 |
+
"grad_norm": 4.910915374755859,
|
| 120 |
+
"learning_rate": 9.535802469135803e-06,
|
| 121 |
+
"loss": 2.329,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4533333333333333,
|
| 126 |
+
"grad_norm": 3.9040019512176514,
|
| 127 |
+
"learning_rate": 9.437037037037038e-06,
|
| 128 |
+
"loss": 2.2805,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.48,
|
| 133 |
+
"grad_norm": 4.538000583648682,
|
| 134 |
+
"learning_rate": 9.338271604938272e-06,
|
| 135 |
+
"loss": 2.2337,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5066666666666667,
|
| 140 |
+
"grad_norm": 4.436681747436523,
|
| 141 |
+
"learning_rate": 9.239506172839507e-06,
|
| 142 |
+
"loss": 2.1707,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5333333333333333,
|
| 147 |
+
"grad_norm": 3.9308009147644043,
|
| 148 |
+
"learning_rate": 9.140740740740741e-06,
|
| 149 |
+
"loss": 2.1456,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.56,
|
| 154 |
+
"grad_norm": 3.86208176612854,
|
| 155 |
+
"learning_rate": 9.041975308641976e-06,
|
| 156 |
+
"loss": 2.1016,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5866666666666667,
|
| 161 |
+
"grad_norm": 3.7303709983825684,
|
| 162 |
+
"learning_rate": 8.94320987654321e-06,
|
| 163 |
+
"loss": 2.0947,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6133333333333333,
|
| 168 |
+
"grad_norm": 3.9554977416992188,
|
| 169 |
+
"learning_rate": 8.844444444444445e-06,
|
| 170 |
+
"loss": 2.0326,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.64,
|
| 175 |
+
"grad_norm": 3.9618735313415527,
|
| 176 |
+
"learning_rate": 8.745679012345679e-06,
|
| 177 |
+
"loss": 2.0283,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6666666666666666,
|
| 182 |
+
"grad_norm": 3.3923730850219727,
|
| 183 |
+
"learning_rate": 8.646913580246914e-06,
|
| 184 |
+
"loss": 1.9994,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.6933333333333334,
|
| 189 |
+
"grad_norm": 3.5262701511383057,
|
| 190 |
+
"learning_rate": 8.54814814814815e-06,
|
| 191 |
+
"loss": 1.9543,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.72,
|
| 196 |
+
"grad_norm": 3.634221076965332,
|
| 197 |
+
"learning_rate": 8.449382716049383e-06,
|
| 198 |
+
"loss": 1.9488,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7466666666666667,
|
| 203 |
+
"grad_norm": 3.6543495655059814,
|
| 204 |
+
"learning_rate": 8.350617283950619e-06,
|
| 205 |
+
"loss": 1.9339,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7733333333333333,
|
| 210 |
+
"grad_norm": 3.7309067249298096,
|
| 211 |
+
"learning_rate": 8.251851851851852e-06,
|
| 212 |
+
"loss": 1.882,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8,
|
| 217 |
+
"grad_norm": 3.5877723693847656,
|
| 218 |
+
"learning_rate": 8.153086419753088e-06,
|
| 219 |
+
"loss": 1.8521,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8266666666666667,
|
| 224 |
+
"grad_norm": 3.463477373123169,
|
| 225 |
+
"learning_rate": 8.054320987654321e-06,
|
| 226 |
+
"loss": 1.8491,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8533333333333334,
|
| 231 |
+
"grad_norm": 3.7584869861602783,
|
| 232 |
+
"learning_rate": 7.955555555555557e-06,
|
| 233 |
+
"loss": 1.841,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.88,
|
| 238 |
+
"grad_norm": 3.6154866218566895,
|
| 239 |
+
"learning_rate": 7.856790123456792e-06,
|
| 240 |
+
"loss": 1.8371,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.9066666666666666,
|
| 245 |
+
"grad_norm": 3.6091232299804688,
|
| 246 |
+
"learning_rate": 7.758024691358026e-06,
|
| 247 |
+
"loss": 1.8111,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9333333333333333,
|
| 252 |
+
"grad_norm": 3.884768009185791,
|
| 253 |
+
"learning_rate": 7.65925925925926e-06,
|
| 254 |
+
"loss": 1.7937,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.96,
|
| 259 |
+
"grad_norm": 4.100072860717773,
|
| 260 |
+
"learning_rate": 7.5604938271604946e-06,
|
| 261 |
+
"loss": 1.7838,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.9866666666666667,
|
| 266 |
+
"grad_norm": 3.37955641746521,
|
| 267 |
+
"learning_rate": 7.461728395061729e-06,
|
| 268 |
+
"loss": 1.7689,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.0133333333333334,
|
| 273 |
+
"grad_norm": 3.240987539291382,
|
| 274 |
+
"learning_rate": 7.3629629629629636e-06,
|
| 275 |
+
"loss": 1.7468,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.04,
|
| 280 |
+
"grad_norm": 3.664125919342041,
|
| 281 |
+
"learning_rate": 7.264197530864198e-06,
|
| 282 |
+
"loss": 1.7248,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.0666666666666667,
|
| 287 |
+
"grad_norm": 3.392308473587036,
|
| 288 |
+
"learning_rate": 7.1654320987654326e-06,
|
| 289 |
+
"loss": 1.7108,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0933333333333333,
|
| 294 |
+
"grad_norm": 3.8562703132629395,
|
| 295 |
+
"learning_rate": 7.066666666666667e-06,
|
| 296 |
+
"loss": 1.7124,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.12,
|
| 301 |
+
"grad_norm": 7.625685214996338,
|
| 302 |
+
"learning_rate": 6.967901234567902e-06,
|
| 303 |
+
"loss": 1.6827,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.1466666666666667,
|
| 308 |
+
"grad_norm": 3.6525189876556396,
|
| 309 |
+
"learning_rate": 6.869135802469137e-06,
|
| 310 |
+
"loss": 1.6883,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.1733333333333333,
|
| 315 |
+
"grad_norm": 3.893947124481201,
|
| 316 |
+
"learning_rate": 6.7703703703703706e-06,
|
| 317 |
+
"loss": 1.6624,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.2,
|
| 322 |
+
"grad_norm": 3.3236780166625977,
|
| 323 |
+
"learning_rate": 6.671604938271605e-06,
|
| 324 |
+
"loss": 1.6615,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.2266666666666666,
|
| 329 |
+
"grad_norm": 3.5743353366851807,
|
| 330 |
+
"learning_rate": 6.57283950617284e-06,
|
| 331 |
+
"loss": 1.6507,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2533333333333334,
|
| 336 |
+
"grad_norm": 3.5603439807891846,
|
| 337 |
+
"learning_rate": 6.474074074074075e-06,
|
| 338 |
+
"loss": 1.6587,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.28,
|
| 343 |
+
"grad_norm": 3.948760747909546,
|
| 344 |
+
"learning_rate": 6.375308641975309e-06,
|
| 345 |
+
"loss": 1.6183,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.3066666666666666,
|
| 350 |
+
"grad_norm": 3.4485912322998047,
|
| 351 |
+
"learning_rate": 6.276543209876543e-06,
|
| 352 |
+
"loss": 1.6288,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.3333333333333333,
|
| 357 |
+
"grad_norm": 3.2528655529022217,
|
| 358 |
+
"learning_rate": 6.177777777777778e-06,
|
| 359 |
+
"loss": 1.6272,
|
| 360 |
+
"step": 5000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3599999999999999,
|
| 364 |
+
"grad_norm": 3.571824073791504,
|
| 365 |
+
"learning_rate": 6.079012345679013e-06,
|
| 366 |
+
"loss": 1.6081,
|
| 367 |
+
"step": 5100
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3866666666666667,
|
| 371 |
+
"grad_norm": 3.4644646644592285,
|
| 372 |
+
"learning_rate": 5.980246913580247e-06,
|
| 373 |
+
"loss": 1.6084,
|
| 374 |
+
"step": 5200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4133333333333333,
|
| 378 |
+
"grad_norm": 3.1932268142700195,
|
| 379 |
+
"learning_rate": 5.881481481481483e-06,
|
| 380 |
+
"loss": 1.59,
|
| 381 |
+
"step": 5300
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.44,
|
| 385 |
+
"grad_norm": 3.6251769065856934,
|
| 386 |
+
"learning_rate": 5.782716049382716e-06,
|
| 387 |
+
"loss": 1.6158,
|
| 388 |
+
"step": 5400
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.4666666666666668,
|
| 392 |
+
"grad_norm": 3.33617901802063,
|
| 393 |
+
"learning_rate": 5.683950617283951e-06,
|
| 394 |
+
"loss": 1.5942,
|
| 395 |
+
"step": 5500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.4933333333333334,
|
| 399 |
+
"grad_norm": 3.5370359420776367,
|
| 400 |
+
"learning_rate": 5.585185185185185e-06,
|
| 401 |
+
"loss": 1.5839,
|
| 402 |
+
"step": 5600
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.52,
|
| 406 |
+
"grad_norm": 3.4808433055877686,
|
| 407 |
+
"learning_rate": 5.486419753086421e-06,
|
| 408 |
+
"loss": 1.5713,
|
| 409 |
+
"step": 5700
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.5466666666666666,
|
| 413 |
+
"grad_norm": 3.199596643447876,
|
| 414 |
+
"learning_rate": 5.387654320987655e-06,
|
| 415 |
+
"loss": 1.5752,
|
| 416 |
+
"step": 5800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.5733333333333333,
|
| 420 |
+
"grad_norm": 3.5203781127929688,
|
| 421 |
+
"learning_rate": 5.288888888888889e-06,
|
| 422 |
+
"loss": 1.5601,
|
| 423 |
+
"step": 5900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.6,
|
| 427 |
+
"grad_norm": 3.5010998249053955,
|
| 428 |
+
"learning_rate": 5.190123456790123e-06,
|
| 429 |
+
"loss": 1.5686,
|
| 430 |
+
"step": 6000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.6266666666666667,
|
| 434 |
+
"grad_norm": 3.3944363594055176,
|
| 435 |
+
"learning_rate": 5.091358024691359e-06,
|
| 436 |
+
"loss": 1.5388,
|
| 437 |
+
"step": 6100
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.6533333333333333,
|
| 441 |
+
"grad_norm": 3.223571538925171,
|
| 442 |
+
"learning_rate": 4.992592592592592e-06,
|
| 443 |
+
"loss": 1.5595,
|
| 444 |
+
"step": 6200
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.6800000000000002,
|
| 448 |
+
"grad_norm": 3.2041091918945312,
|
| 449 |
+
"learning_rate": 4.893827160493828e-06,
|
| 450 |
+
"loss": 1.5533,
|
| 451 |
+
"step": 6300
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.7066666666666666,
|
| 455 |
+
"grad_norm": 3.480818033218384,
|
| 456 |
+
"learning_rate": 4.795061728395062e-06,
|
| 457 |
+
"loss": 1.5388,
|
| 458 |
+
"step": 6400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.7333333333333334,
|
| 462 |
+
"grad_norm": 3.6483476161956787,
|
| 463 |
+
"learning_rate": 4.696296296296297e-06,
|
| 464 |
+
"loss": 1.5365,
|
| 465 |
+
"step": 6500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.76,
|
| 469 |
+
"grad_norm": 3.3835060596466064,
|
| 470 |
+
"learning_rate": 4.597530864197531e-06,
|
| 471 |
+
"loss": 1.5209,
|
| 472 |
+
"step": 6600
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.7866666666666666,
|
| 476 |
+
"grad_norm": 3.4606142044067383,
|
| 477 |
+
"learning_rate": 4.498765432098766e-06,
|
| 478 |
+
"loss": 1.5244,
|
| 479 |
+
"step": 6700
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.8133333333333335,
|
| 483 |
+
"grad_norm": 3.4562504291534424,
|
| 484 |
+
"learning_rate": 4.4e-06,
|
| 485 |
+
"loss": 1.5201,
|
| 486 |
+
"step": 6800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.8399999999999999,
|
| 490 |
+
"grad_norm": 3.1761395931243896,
|
| 491 |
+
"learning_rate": 4.3012345679012356e-06,
|
| 492 |
+
"loss": 1.517,
|
| 493 |
+
"step": 6900
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.8666666666666667,
|
| 497 |
+
"grad_norm": 3.3345909118652344,
|
| 498 |
+
"learning_rate": 4.202469135802469e-06,
|
| 499 |
+
"loss": 1.519,
|
| 500 |
+
"step": 7000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.8933333333333333,
|
| 504 |
+
"grad_norm": 3.478909492492676,
|
| 505 |
+
"learning_rate": 4.1037037037037046e-06,
|
| 506 |
+
"loss": 1.5059,
|
| 507 |
+
"step": 7100
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.92,
|
| 511 |
+
"grad_norm": 3.1588165760040283,
|
| 512 |
+
"learning_rate": 4.004938271604938e-06,
|
| 513 |
+
"loss": 1.5096,
|
| 514 |
+
"step": 7200
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.9466666666666668,
|
| 518 |
+
"grad_norm": 3.4162404537200928,
|
| 519 |
+
"learning_rate": 3.9061728395061736e-06,
|
| 520 |
+
"loss": 1.5212,
|
| 521 |
+
"step": 7300
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.9733333333333334,
|
| 525 |
+
"grad_norm": 3.6003329753875732,
|
| 526 |
+
"learning_rate": 3.807407407407408e-06,
|
| 527 |
+
"loss": 1.4954,
|
| 528 |
+
"step": 7400
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.0,
|
| 532 |
+
"grad_norm": 3.615638256072998,
|
| 533 |
+
"learning_rate": 3.708641975308642e-06,
|
| 534 |
+
"loss": 1.4833,
|
| 535 |
+
"step": 7500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.026666666666667,
|
| 539 |
+
"grad_norm": 3.468055248260498,
|
| 540 |
+
"learning_rate": 3.609876543209877e-06,
|
| 541 |
+
"loss": 1.46,
|
| 542 |
+
"step": 7600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.0533333333333332,
|
| 546 |
+
"grad_norm": 3.4660258293151855,
|
| 547 |
+
"learning_rate": 3.511111111111111e-06,
|
| 548 |
+
"loss": 1.4648,
|
| 549 |
+
"step": 7700
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.08,
|
| 553 |
+
"grad_norm": 3.182377815246582,
|
| 554 |
+
"learning_rate": 3.412345679012346e-06,
|
| 555 |
+
"loss": 1.4711,
|
| 556 |
+
"step": 7800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.1066666666666665,
|
| 560 |
+
"grad_norm": 3.9496777057647705,
|
| 561 |
+
"learning_rate": 3.31358024691358e-06,
|
| 562 |
+
"loss": 1.46,
|
| 563 |
+
"step": 7900
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.1333333333333333,
|
| 567 |
+
"grad_norm": 3.103764533996582,
|
| 568 |
+
"learning_rate": 3.214814814814815e-06,
|
| 569 |
+
"loss": 1.4573,
|
| 570 |
+
"step": 8000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.16,
|
| 574 |
+
"grad_norm": 3.518872022628784,
|
| 575 |
+
"learning_rate": 3.11604938271605e-06,
|
| 576 |
+
"loss": 1.467,
|
| 577 |
+
"step": 8100
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.1866666666666665,
|
| 581 |
+
"grad_norm": 3.5382354259490967,
|
| 582 |
+
"learning_rate": 3.017283950617284e-06,
|
| 583 |
+
"loss": 1.4533,
|
| 584 |
+
"step": 8200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.2133333333333334,
|
| 588 |
+
"grad_norm": 3.7412240505218506,
|
| 589 |
+
"learning_rate": 2.918518518518519e-06,
|
| 590 |
+
"loss": 1.4548,
|
| 591 |
+
"step": 8300
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.24,
|
| 595 |
+
"grad_norm": 3.4695069789886475,
|
| 596 |
+
"learning_rate": 2.819753086419753e-06,
|
| 597 |
+
"loss": 1.4342,
|
| 598 |
+
"step": 8400
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.2666666666666666,
|
| 602 |
+
"grad_norm": 3.71409010887146,
|
| 603 |
+
"learning_rate": 2.720987654320988e-06,
|
| 604 |
+
"loss": 1.4538,
|
| 605 |
+
"step": 8500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.2933333333333334,
|
| 609 |
+
"grad_norm": 3.422849655151367,
|
| 610 |
+
"learning_rate": 2.6222222222222225e-06,
|
| 611 |
+
"loss": 1.4491,
|
| 612 |
+
"step": 8600
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.32,
|
| 616 |
+
"grad_norm": 3.2974777221679688,
|
| 617 |
+
"learning_rate": 2.523456790123457e-06,
|
| 618 |
+
"loss": 1.4472,
|
| 619 |
+
"step": 8700
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.3466666666666667,
|
| 623 |
+
"grad_norm": 3.2598888874053955,
|
| 624 |
+
"learning_rate": 2.4246913580246915e-06,
|
| 625 |
+
"loss": 1.4377,
|
| 626 |
+
"step": 8800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.3733333333333335,
|
| 630 |
+
"grad_norm": 3.5371761322021484,
|
| 631 |
+
"learning_rate": 2.3259259259259264e-06,
|
| 632 |
+
"loss": 1.4451,
|
| 633 |
+
"step": 8900
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.4,
|
| 637 |
+
"grad_norm": 3.5494816303253174,
|
| 638 |
+
"learning_rate": 2.227160493827161e-06,
|
| 639 |
+
"loss": 1.4311,
|
| 640 |
+
"step": 9000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.4266666666666667,
|
| 644 |
+
"grad_norm": 2.9961225986480713,
|
| 645 |
+
"learning_rate": 2.1283950617283954e-06,
|
| 646 |
+
"loss": 1.438,
|
| 647 |
+
"step": 9100
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.453333333333333,
|
| 651 |
+
"grad_norm": 3.317133665084839,
|
| 652 |
+
"learning_rate": 2.02962962962963e-06,
|
| 653 |
+
"loss": 1.4434,
|
| 654 |
+
"step": 9200
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.48,
|
| 658 |
+
"grad_norm": 3.474153995513916,
|
| 659 |
+
"learning_rate": 1.9308641975308644e-06,
|
| 660 |
+
"loss": 1.4393,
|
| 661 |
+
"step": 9300
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.506666666666667,
|
| 665 |
+
"grad_norm": 3.3163111209869385,
|
| 666 |
+
"learning_rate": 1.8320987654320991e-06,
|
| 667 |
+
"loss": 1.4309,
|
| 668 |
+
"step": 9400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.533333333333333,
|
| 672 |
+
"grad_norm": 3.372511863708496,
|
| 673 |
+
"learning_rate": 1.7333333333333336e-06,
|
| 674 |
+
"loss": 1.43,
|
| 675 |
+
"step": 9500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.56,
|
| 679 |
+
"grad_norm": 3.3499677181243896,
|
| 680 |
+
"learning_rate": 1.6345679012345681e-06,
|
| 681 |
+
"loss": 1.4234,
|
| 682 |
+
"step": 9600
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.586666666666667,
|
| 686 |
+
"grad_norm": 3.7494187355041504,
|
| 687 |
+
"learning_rate": 1.5358024691358026e-06,
|
| 688 |
+
"loss": 1.4138,
|
| 689 |
+
"step": 9700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.6133333333333333,
|
| 693 |
+
"grad_norm": 3.28361439704895,
|
| 694 |
+
"learning_rate": 1.437037037037037e-06,
|
| 695 |
+
"loss": 1.4271,
|
| 696 |
+
"step": 9800
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.64,
|
| 700 |
+
"grad_norm": 3.311584711074829,
|
| 701 |
+
"learning_rate": 1.3382716049382718e-06,
|
| 702 |
+
"loss": 1.4276,
|
| 703 |
+
"step": 9900
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.6666666666666665,
|
| 707 |
+
"grad_norm": 3.294921636581421,
|
| 708 |
+
"learning_rate": 1.2404938271604939e-06,
|
| 709 |
+
"loss": 1.41,
|
| 710 |
+
"step": 10000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.6933333333333334,
|
| 714 |
+
"grad_norm": 3.2336692810058594,
|
| 715 |
+
"learning_rate": 1.1417283950617284e-06,
|
| 716 |
+
"loss": 1.415,
|
| 717 |
+
"step": 10100
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.7199999999999998,
|
| 721 |
+
"grad_norm": 3.503819227218628,
|
| 722 |
+
"learning_rate": 1.042962962962963e-06,
|
| 723 |
+
"loss": 1.4112,
|
| 724 |
+
"step": 10200
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.7466666666666666,
|
| 728 |
+
"grad_norm": 3.102999210357666,
|
| 729 |
+
"learning_rate": 9.441975308641977e-07,
|
| 730 |
+
"loss": 1.4167,
|
| 731 |
+
"step": 10300
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.7733333333333334,
|
| 735 |
+
"grad_norm": 3.2620484828948975,
|
| 736 |
+
"learning_rate": 8.454320987654322e-07,
|
| 737 |
+
"loss": 1.4242,
|
| 738 |
+
"step": 10400
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.8,
|
| 742 |
+
"grad_norm": 3.2163949012756348,
|
| 743 |
+
"learning_rate": 7.466666666666668e-07,
|
| 744 |
+
"loss": 1.4281,
|
| 745 |
+
"step": 10500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.8266666666666667,
|
| 749 |
+
"grad_norm": 3.1168317794799805,
|
| 750 |
+
"learning_rate": 6.479012345679013e-07,
|
| 751 |
+
"loss": 1.4166,
|
| 752 |
+
"step": 10600
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.8533333333333335,
|
| 756 |
+
"grad_norm": 3.3667855262756348,
|
| 757 |
+
"learning_rate": 5.491358024691359e-07,
|
| 758 |
+
"loss": 1.4196,
|
| 759 |
+
"step": 10700
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.88,
|
| 763 |
+
"grad_norm": 3.4047067165374756,
|
| 764 |
+
"learning_rate": 4.503703703703704e-07,
|
| 765 |
+
"loss": 1.4116,
|
| 766 |
+
"step": 10800
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.9066666666666667,
|
| 770 |
+
"grad_norm": 3.1459200382232666,
|
| 771 |
+
"learning_rate": 3.5160493827160494e-07,
|
| 772 |
+
"loss": 1.4082,
|
| 773 |
+
"step": 10900
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.9333333333333336,
|
| 777 |
+
"grad_norm": 3.670799732208252,
|
| 778 |
+
"learning_rate": 2.528395061728395e-07,
|
| 779 |
+
"loss": 1.4204,
|
| 780 |
+
"step": 11000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.96,
|
| 784 |
+
"grad_norm": 3.3167898654937744,
|
| 785 |
+
"learning_rate": 1.540740740740741e-07,
|
| 786 |
+
"loss": 1.3972,
|
| 787 |
+
"step": 11100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.986666666666667,
|
| 791 |
+
"grad_norm": 3.06726336479187,
|
| 792 |
+
"learning_rate": 5.5308641975308646e-08,
|
| 793 |
+
"loss": 1.4173,
|
| 794 |
+
"step": 11200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.0,
|
| 798 |
+
"step": 11250,
|
| 799 |
+
"total_flos": 1.0681625740050432e+20,
|
| 800 |
+
"train_loss": 1.8866207526312935,
|
| 801 |
+
"train_runtime": 25047.9369,
|
| 802 |
+
"train_samples_per_second": 7.186,
|
| 803 |
+
"train_steps_per_second": 0.449
|
| 804 |
+
}
|
| 805 |
+
],
|
| 806 |
+
"logging_steps": 100,
|
| 807 |
+
"max_steps": 11250,
|
| 808 |
+
"num_input_tokens_seen": 0,
|
| 809 |
+
"num_train_epochs": 3,
|
| 810 |
+
"save_steps": 500,
|
| 811 |
+
"stateful_callbacks": {
|
| 812 |
+
"TrainerControl": {
|
| 813 |
+
"args": {
|
| 814 |
+
"should_epoch_stop": false,
|
| 815 |
+
"should_evaluate": false,
|
| 816 |
+
"should_log": false,
|
| 817 |
+
"should_save": true,
|
| 818 |
+
"should_training_stop": true
|
| 819 |
+
},
|
| 820 |
+
"attributes": {}
|
| 821 |
+
}
|
| 822 |
+
},
|
| 823 |
+
"total_flos": 1.0681625740050432e+20,
|
| 824 |
+
"train_batch_size": 4,
|
| 825 |
+
"trial_name": null,
|
| 826 |
+
"trial_params": null
|
| 827 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c76d35fb5021a5c8fd8d86ec0d3ece725856cddf823f9ab56ff2c69a3b018819
|
| 3 |
+
size 5368
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|