End of training
Browse files- all_results.json +12 -0
- eval_results.json +7 -0
- merges.txt +0 -0
- preprocessor_config.json +45 -0
- runs/May05_15-00-00_cbb6f6ab0fba/events.out.tfevents.1714926878.cbb6f6ab0fba.18514.1 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +35 -0
- train_results.json +8 -0
- trainer_state.json +522 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 1.4227830171585083,
|
| 4 |
+
"eval_runtime": 69.4956,
|
| 5 |
+
"eval_samples_per_second": 2.158,
|
| 6 |
+
"eval_steps_per_second": 0.043,
|
| 7 |
+
"total_flos": 115984993944204.0,
|
| 8 |
+
"train_loss": 1.1255573146045208,
|
| 9 |
+
"train_runtime": 4694.1264,
|
| 10 |
+
"train_samples_per_second": 0.425,
|
| 11 |
+
"train_steps_per_second": 0.007
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 1.4227830171585083,
|
| 4 |
+
"eval_runtime": 69.4956,
|
| 5 |
+
"eval_samples_per_second": 2.158,
|
| 6 |
+
"eval_steps_per_second": 0.043
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_center_crop",
|
| 8 |
+
"crop_size",
|
| 9 |
+
"do_rescale",
|
| 10 |
+
"rescale_factor",
|
| 11 |
+
"do_normalize",
|
| 12 |
+
"image_mean",
|
| 13 |
+
"image_std",
|
| 14 |
+
"do_convert_rgb",
|
| 15 |
+
"return_tensors",
|
| 16 |
+
"data_format",
|
| 17 |
+
"input_data_format"
|
| 18 |
+
],
|
| 19 |
+
"crop_size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
},
|
| 23 |
+
"do_center_crop": true,
|
| 24 |
+
"do_convert_rgb": true,
|
| 25 |
+
"do_normalize": true,
|
| 26 |
+
"do_rescale": true,
|
| 27 |
+
"do_resize": true,
|
| 28 |
+
"image_mean": [
|
| 29 |
+
0.48145466,
|
| 30 |
+
0.4578275,
|
| 31 |
+
0.40821073
|
| 32 |
+
],
|
| 33 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 34 |
+
"image_std": [
|
| 35 |
+
0.26862954,
|
| 36 |
+
0.26130258,
|
| 37 |
+
0.27577711
|
| 38 |
+
],
|
| 39 |
+
"processor_class": "CLIPProcessor",
|
| 40 |
+
"resample": 3,
|
| 41 |
+
"rescale_factor": 0.00392156862745098,
|
| 42 |
+
"size": {
|
| 43 |
+
"shortest_edge": 224
|
| 44 |
+
}
|
| 45 |
+
}
|
runs/May05_15-00-00_cbb6f6ab0fba/events.out.tfevents.1714926878.cbb6f6ab0fba.18514.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d1e68327f4fa5e98bbd74c86566219289bb890cb4a7db37cea24aa569d8cba5
|
| 3 |
+
size 354
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|startoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": true,
|
| 23 |
+
"do_lower_case": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"max_length": null,
|
| 27 |
+
"model_max_length": 77,
|
| 28 |
+
"pad_to_multiple_of": null,
|
| 29 |
+
"pad_token": "<|endoftext|>",
|
| 30 |
+
"pad_token_type_id": 0,
|
| 31 |
+
"padding_side": "right",
|
| 32 |
+
"processor_class": "CLIPProcessor",
|
| 33 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 34 |
+
"unk_token": "<|endoftext|>"
|
| 35 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 115984993944204.0,
|
| 4 |
+
"train_loss": 1.1255573146045208,
|
| 5 |
+
"train_runtime": 4694.1264,
|
| 6 |
+
"train_samples_per_second": 0.425,
|
| 7 |
+
"train_steps_per_second": 0.007
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,522 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 1.0,
|
| 6 |
+
"global_step": 32,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0625,
|
| 13 |
+
"grad_norm": 125.37348937988281,
|
| 14 |
+
"learning_rate": 4.8437500000000005e-05,
|
| 15 |
+
"loss": 1.8261,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0625,
|
| 20 |
+
"eval_loss": 1.7808233499526978,
|
| 21 |
+
"eval_runtime": 101.8647,
|
| 22 |
+
"eval_samples_per_second": 1.473,
|
| 23 |
+
"eval_steps_per_second": 0.029,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.125,
|
| 28 |
+
"grad_norm": 251.37063598632812,
|
| 29 |
+
"learning_rate": 4.6875e-05,
|
| 30 |
+
"loss": 1.7935,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.125,
|
| 35 |
+
"eval_loss": 1.623749852180481,
|
| 36 |
+
"eval_runtime": 94.4381,
|
| 37 |
+
"eval_samples_per_second": 1.588,
|
| 38 |
+
"eval_steps_per_second": 0.032,
|
| 39 |
+
"step": 2
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1875,
|
| 43 |
+
"grad_norm": 117.00857543945312,
|
| 44 |
+
"learning_rate": 4.5312500000000004e-05,
|
| 45 |
+
"loss": 2.2498,
|
| 46 |
+
"step": 3
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.1875,
|
| 50 |
+
"eval_loss": 1.741827130317688,
|
| 51 |
+
"eval_runtime": 70.4069,
|
| 52 |
+
"eval_samples_per_second": 2.13,
|
| 53 |
+
"eval_steps_per_second": 0.043,
|
| 54 |
+
"step": 3
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.25,
|
| 58 |
+
"grad_norm": 102.61508178710938,
|
| 59 |
+
"learning_rate": 4.375e-05,
|
| 60 |
+
"loss": 1.9536,
|
| 61 |
+
"step": 4
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.25,
|
| 65 |
+
"eval_loss": 1.7777817249298096,
|
| 66 |
+
"eval_runtime": 72.2698,
|
| 67 |
+
"eval_samples_per_second": 2.076,
|
| 68 |
+
"eval_steps_per_second": 0.042,
|
| 69 |
+
"step": 4
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.3125,
|
| 73 |
+
"grad_norm": 73.9283676147461,
|
| 74 |
+
"learning_rate": 4.21875e-05,
|
| 75 |
+
"loss": 2.1207,
|
| 76 |
+
"step": 5
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.3125,
|
| 80 |
+
"eval_loss": 1.7881625890731812,
|
| 81 |
+
"eval_runtime": 70.2676,
|
| 82 |
+
"eval_samples_per_second": 2.135,
|
| 83 |
+
"eval_steps_per_second": 0.043,
|
| 84 |
+
"step": 5
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.375,
|
| 88 |
+
"grad_norm": 82.38343811035156,
|
| 89 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 90 |
+
"loss": 2.1623,
|
| 91 |
+
"step": 6
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.375,
|
| 95 |
+
"eval_loss": 1.8577982187271118,
|
| 96 |
+
"eval_runtime": 72.0998,
|
| 97 |
+
"eval_samples_per_second": 2.08,
|
| 98 |
+
"eval_steps_per_second": 0.042,
|
| 99 |
+
"step": 6
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.4375,
|
| 103 |
+
"grad_norm": 57.1233024597168,
|
| 104 |
+
"learning_rate": 3.90625e-05,
|
| 105 |
+
"loss": 2.0764,
|
| 106 |
+
"step": 7
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.4375,
|
| 110 |
+
"eval_loss": 1.8867578506469727,
|
| 111 |
+
"eval_runtime": 88.6197,
|
| 112 |
+
"eval_samples_per_second": 1.693,
|
| 113 |
+
"eval_steps_per_second": 0.034,
|
| 114 |
+
"step": 7
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5,
|
| 118 |
+
"grad_norm": 56.74623107910156,
|
| 119 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 120 |
+
"loss": 2.206,
|
| 121 |
+
"step": 8
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5,
|
| 125 |
+
"eval_loss": 1.8570754528045654,
|
| 126 |
+
"eval_runtime": 68.277,
|
| 127 |
+
"eval_samples_per_second": 2.197,
|
| 128 |
+
"eval_steps_per_second": 0.044,
|
| 129 |
+
"step": 8
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5625,
|
| 133 |
+
"grad_norm": 55.427146911621094,
|
| 134 |
+
"learning_rate": 3.59375e-05,
|
| 135 |
+
"loss": 2.2791,
|
| 136 |
+
"step": 9
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5625,
|
| 140 |
+
"eval_loss": 1.8133898973464966,
|
| 141 |
+
"eval_runtime": 67.77,
|
| 142 |
+
"eval_samples_per_second": 2.213,
|
| 143 |
+
"eval_steps_per_second": 0.044,
|
| 144 |
+
"step": 9
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.625,
|
| 148 |
+
"grad_norm": 48.58964157104492,
|
| 149 |
+
"learning_rate": 3.4375e-05,
|
| 150 |
+
"loss": 2.2276,
|
| 151 |
+
"step": 10
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.625,
|
| 155 |
+
"eval_loss": 1.759128451347351,
|
| 156 |
+
"eval_runtime": 66.1185,
|
| 157 |
+
"eval_samples_per_second": 2.269,
|
| 158 |
+
"eval_steps_per_second": 0.045,
|
| 159 |
+
"step": 10
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.6875,
|
| 163 |
+
"grad_norm": 58.89248275756836,
|
| 164 |
+
"learning_rate": 3.2812500000000005e-05,
|
| 165 |
+
"loss": 1.826,
|
| 166 |
+
"step": 11
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.6875,
|
| 170 |
+
"eval_loss": 1.6688445806503296,
|
| 171 |
+
"eval_runtime": 67.5679,
|
| 172 |
+
"eval_samples_per_second": 2.22,
|
| 173 |
+
"eval_steps_per_second": 0.044,
|
| 174 |
+
"step": 11
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.75,
|
| 178 |
+
"grad_norm": 46.2577018737793,
|
| 179 |
+
"learning_rate": 3.125e-05,
|
| 180 |
+
"loss": 1.668,
|
| 181 |
+
"step": 12
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.75,
|
| 185 |
+
"eval_loss": 1.5710270404815674,
|
| 186 |
+
"eval_runtime": 67.265,
|
| 187 |
+
"eval_samples_per_second": 2.23,
|
| 188 |
+
"eval_steps_per_second": 0.045,
|
| 189 |
+
"step": 12
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.8125,
|
| 193 |
+
"grad_norm": 42.970054626464844,
|
| 194 |
+
"learning_rate": 2.96875e-05,
|
| 195 |
+
"loss": 1.8039,
|
| 196 |
+
"step": 13
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.8125,
|
| 200 |
+
"eval_loss": 1.527113914489746,
|
| 201 |
+
"eval_runtime": 66.977,
|
| 202 |
+
"eval_samples_per_second": 2.24,
|
| 203 |
+
"eval_steps_per_second": 0.045,
|
| 204 |
+
"step": 13
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.875,
|
| 208 |
+
"grad_norm": 48.52293395996094,
|
| 209 |
+
"learning_rate": 2.8125000000000003e-05,
|
| 210 |
+
"loss": 1.7761,
|
| 211 |
+
"step": 14
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.875,
|
| 215 |
+
"eval_loss": 1.497421383857727,
|
| 216 |
+
"eval_runtime": 68.3346,
|
| 217 |
+
"eval_samples_per_second": 2.195,
|
| 218 |
+
"eval_steps_per_second": 0.044,
|
| 219 |
+
"step": 14
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9375,
|
| 223 |
+
"grad_norm": 43.09657287597656,
|
| 224 |
+
"learning_rate": 2.6562500000000002e-05,
|
| 225 |
+
"loss": 1.5512,
|
| 226 |
+
"step": 15
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9375,
|
| 230 |
+
"eval_loss": 1.479906439781189,
|
| 231 |
+
"eval_runtime": 67.7193,
|
| 232 |
+
"eval_samples_per_second": 2.215,
|
| 233 |
+
"eval_steps_per_second": 0.044,
|
| 234 |
+
"step": 15
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0,
|
| 238 |
+
"grad_norm": 49.768165588378906,
|
| 239 |
+
"learning_rate": 2.5e-05,
|
| 240 |
+
"loss": 1.0115,
|
| 241 |
+
"step": 16
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0,
|
| 245 |
+
"eval_loss": 1.4686092138290405,
|
| 246 |
+
"eval_runtime": 65.0137,
|
| 247 |
+
"eval_samples_per_second": 2.307,
|
| 248 |
+
"eval_steps_per_second": 0.046,
|
| 249 |
+
"step": 16
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0625,
|
| 253 |
+
"grad_norm": 24.204669952392578,
|
| 254 |
+
"learning_rate": 2.34375e-05,
|
| 255 |
+
"loss": 0.4346,
|
| 256 |
+
"step": 17
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.0625,
|
| 260 |
+
"eval_loss": 1.4616279602050781,
|
| 261 |
+
"eval_runtime": 66.0842,
|
| 262 |
+
"eval_samples_per_second": 2.27,
|
| 263 |
+
"eval_steps_per_second": 0.045,
|
| 264 |
+
"step": 17
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.125,
|
| 268 |
+
"grad_norm": 18.588682174682617,
|
| 269 |
+
"learning_rate": 2.1875e-05,
|
| 270 |
+
"loss": 0.3421,
|
| 271 |
+
"step": 18
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.125,
|
| 275 |
+
"eval_loss": 1.4559637308120728,
|
| 276 |
+
"eval_runtime": 67.549,
|
| 277 |
+
"eval_samples_per_second": 2.221,
|
| 278 |
+
"eval_steps_per_second": 0.044,
|
| 279 |
+
"step": 18
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.1875,
|
| 283 |
+
"grad_norm": 20.04482078552246,
|
| 284 |
+
"learning_rate": 2.0312500000000002e-05,
|
| 285 |
+
"loss": 0.3134,
|
| 286 |
+
"step": 19
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.1875,
|
| 290 |
+
"eval_loss": 1.4582462310791016,
|
| 291 |
+
"eval_runtime": 65.9148,
|
| 292 |
+
"eval_samples_per_second": 2.276,
|
| 293 |
+
"eval_steps_per_second": 0.046,
|
| 294 |
+
"step": 19
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.25,
|
| 298 |
+
"grad_norm": 23.909494400024414,
|
| 299 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 300 |
+
"loss": 0.2237,
|
| 301 |
+
"step": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.25,
|
| 305 |
+
"eval_loss": 1.467896819114685,
|
| 306 |
+
"eval_runtime": 66.108,
|
| 307 |
+
"eval_samples_per_second": 2.269,
|
| 308 |
+
"eval_steps_per_second": 0.045,
|
| 309 |
+
"step": 20
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.3125,
|
| 313 |
+
"grad_norm": 33.90362548828125,
|
| 314 |
+
"learning_rate": 1.71875e-05,
|
| 315 |
+
"loss": 0.6518,
|
| 316 |
+
"step": 21
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.3125,
|
| 320 |
+
"eval_loss": 1.4688968658447266,
|
| 321 |
+
"eval_runtime": 69.8941,
|
| 322 |
+
"eval_samples_per_second": 2.146,
|
| 323 |
+
"eval_steps_per_second": 0.043,
|
| 324 |
+
"step": 21
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.375,
|
| 328 |
+
"grad_norm": 30.035762786865234,
|
| 329 |
+
"learning_rate": 1.5625e-05,
|
| 330 |
+
"loss": 0.3559,
|
| 331 |
+
"step": 22
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.375,
|
| 335 |
+
"eval_loss": 1.4729983806610107,
|
| 336 |
+
"eval_runtime": 67.5966,
|
| 337 |
+
"eval_samples_per_second": 2.219,
|
| 338 |
+
"eval_steps_per_second": 0.044,
|
| 339 |
+
"step": 22
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4375,
|
| 343 |
+
"grad_norm": 28.968109130859375,
|
| 344 |
+
"learning_rate": 1.4062500000000001e-05,
|
| 345 |
+
"loss": 0.38,
|
| 346 |
+
"step": 23
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4375,
|
| 350 |
+
"eval_loss": 1.4652482271194458,
|
| 351 |
+
"eval_runtime": 68.3514,
|
| 352 |
+
"eval_samples_per_second": 2.195,
|
| 353 |
+
"eval_steps_per_second": 0.044,
|
| 354 |
+
"step": 23
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.5,
|
| 358 |
+
"grad_norm": 29.879552841186523,
|
| 359 |
+
"learning_rate": 1.25e-05,
|
| 360 |
+
"loss": 0.3887,
|
| 361 |
+
"step": 24
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.5,
|
| 365 |
+
"eval_loss": 1.4595154523849487,
|
| 366 |
+
"eval_runtime": 66.69,
|
| 367 |
+
"eval_samples_per_second": 2.249,
|
| 368 |
+
"eval_steps_per_second": 0.045,
|
| 369 |
+
"step": 24
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.5625,
|
| 373 |
+
"grad_norm": 28.710205078125,
|
| 374 |
+
"learning_rate": 1.09375e-05,
|
| 375 |
+
"loss": 0.3202,
|
| 376 |
+
"step": 25
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.5625,
|
| 380 |
+
"eval_loss": 1.4468400478363037,
|
| 381 |
+
"eval_runtime": 68.3647,
|
| 382 |
+
"eval_samples_per_second": 2.194,
|
| 383 |
+
"eval_steps_per_second": 0.044,
|
| 384 |
+
"step": 25
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.625,
|
| 388 |
+
"grad_norm": 27.124183654785156,
|
| 389 |
+
"learning_rate": 9.375000000000001e-06,
|
| 390 |
+
"loss": 0.2525,
|
| 391 |
+
"step": 26
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.625,
|
| 395 |
+
"eval_loss": 1.438510775566101,
|
| 396 |
+
"eval_runtime": 65.3338,
|
| 397 |
+
"eval_samples_per_second": 2.296,
|
| 398 |
+
"eval_steps_per_second": 0.046,
|
| 399 |
+
"step": 26
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.6875,
|
| 403 |
+
"grad_norm": 31.146799087524414,
|
| 404 |
+
"learning_rate": 7.8125e-06,
|
| 405 |
+
"loss": 0.5361,
|
| 406 |
+
"step": 27
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.6875,
|
| 410 |
+
"eval_loss": 1.4363871812820435,
|
| 411 |
+
"eval_runtime": 79.7494,
|
| 412 |
+
"eval_samples_per_second": 1.881,
|
| 413 |
+
"eval_steps_per_second": 0.038,
|
| 414 |
+
"step": 27
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.75,
|
| 418 |
+
"grad_norm": 30.060962677001953,
|
| 419 |
+
"learning_rate": 6.25e-06,
|
| 420 |
+
"loss": 0.3427,
|
| 421 |
+
"step": 28
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.75,
|
| 425 |
+
"eval_loss": 1.435764193534851,
|
| 426 |
+
"eval_runtime": 89.795,
|
| 427 |
+
"eval_samples_per_second": 1.67,
|
| 428 |
+
"eval_steps_per_second": 0.033,
|
| 429 |
+
"step": 28
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.8125,
|
| 433 |
+
"grad_norm": 28.790109634399414,
|
| 434 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 435 |
+
"loss": 0.2529,
|
| 436 |
+
"step": 29
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.8125,
|
| 440 |
+
"eval_loss": 1.4345921277999878,
|
| 441 |
+
"eval_runtime": 67.6708,
|
| 442 |
+
"eval_samples_per_second": 2.217,
|
| 443 |
+
"eval_steps_per_second": 0.044,
|
| 444 |
+
"step": 29
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.875,
|
| 448 |
+
"grad_norm": 26.701284408569336,
|
| 449 |
+
"learning_rate": 3.125e-06,
|
| 450 |
+
"loss": 0.1857,
|
| 451 |
+
"step": 30
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.875,
|
| 455 |
+
"eval_loss": 1.4300572872161865,
|
| 456 |
+
"eval_runtime": 68.0502,
|
| 457 |
+
"eval_samples_per_second": 2.204,
|
| 458 |
+
"eval_steps_per_second": 0.044,
|
| 459 |
+
"step": 30
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.9375,
|
| 463 |
+
"grad_norm": 32.15977096557617,
|
| 464 |
+
"learning_rate": 1.5625e-06,
|
| 465 |
+
"loss": 0.3143,
|
| 466 |
+
"step": 31
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.9375,
|
| 470 |
+
"eval_loss": 1.424769639968872,
|
| 471 |
+
"eval_runtime": 66.6233,
|
| 472 |
+
"eval_samples_per_second": 2.251,
|
| 473 |
+
"eval_steps_per_second": 0.045,
|
| 474 |
+
"step": 31
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.0,
|
| 478 |
+
"grad_norm": 24.524354934692383,
|
| 479 |
+
"learning_rate": 0.0,
|
| 480 |
+
"loss": 0.1912,
|
| 481 |
+
"step": 32
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.0,
|
| 485 |
+
"eval_loss": 1.4227830171585083,
|
| 486 |
+
"eval_runtime": 68.629,
|
| 487 |
+
"eval_samples_per_second": 2.186,
|
| 488 |
+
"eval_steps_per_second": 0.044,
|
| 489 |
+
"step": 32
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.0,
|
| 493 |
+
"step": 32,
|
| 494 |
+
"total_flos": 115984993944204.0,
|
| 495 |
+
"train_loss": 1.1255573146045208,
|
| 496 |
+
"train_runtime": 4694.1264,
|
| 497 |
+
"train_samples_per_second": 0.425,
|
| 498 |
+
"train_steps_per_second": 0.007
|
| 499 |
+
}
|
| 500 |
+
],
|
| 501 |
+
"logging_steps": 1.0,
|
| 502 |
+
"max_steps": 32,
|
| 503 |
+
"num_input_tokens_seen": 0,
|
| 504 |
+
"num_train_epochs": 2,
|
| 505 |
+
"save_steps": 500,
|
| 506 |
+
"stateful_callbacks": {
|
| 507 |
+
"TrainerControl": {
|
| 508 |
+
"args": {
|
| 509 |
+
"should_epoch_stop": false,
|
| 510 |
+
"should_evaluate": false,
|
| 511 |
+
"should_log": false,
|
| 512 |
+
"should_save": false,
|
| 513 |
+
"should_training_stop": false
|
| 514 |
+
},
|
| 515 |
+
"attributes": {}
|
| 516 |
+
}
|
| 517 |
+
},
|
| 518 |
+
"total_flos": 115984993944204.0,
|
| 519 |
+
"train_batch_size": 64,
|
| 520 |
+
"trial_name": null,
|
| 521 |
+
"trial_params": null
|
| 522 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|