Commit
•
e0e0344
1
Parent(s):
3422060
Upload 2 files
Browse files- tokenizer_config.json +12 -0
- trainer_state.json +73 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"model_max_length": 512,
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"separate_vocabs": false,
|
| 7 |
+
"source_lang": "en",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"target_lang": "fr",
|
| 10 |
+
"tokenizer_class": "MarianTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 4260,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.7,
|
| 12 |
+
"learning_rate": 4.413145539906103e-05,
|
| 13 |
+
"loss": 0.9331,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.41,
|
| 18 |
+
"learning_rate": 3.826291079812207e-05,
|
| 19 |
+
"loss": 0.521,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.11,
|
| 24 |
+
"learning_rate": 3.23943661971831e-05,
|
| 25 |
+
"loss": 0.3464,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.82,
|
| 30 |
+
"learning_rate": 2.6525821596244134e-05,
|
| 31 |
+
"loss": 0.2114,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.52,
|
| 36 |
+
"learning_rate": 2.0657276995305167e-05,
|
| 37 |
+
"loss": 0.1467,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 4.23,
|
| 42 |
+
"learning_rate": 1.4788732394366198e-05,
|
| 43 |
+
"loss": 0.1109,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.93,
|
| 48 |
+
"learning_rate": 8.92018779342723e-06,
|
| 49 |
+
"loss": 0.0767,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 5.63,
|
| 54 |
+
"learning_rate": 3.051643192488263e-06,
|
| 55 |
+
"loss": 0.0504,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 6.0,
|
| 60 |
+
"step": 4260,
|
| 61 |
+
"total_flos": 72510721228800.0,
|
| 62 |
+
"train_loss": 0.28417864718907315,
|
| 63 |
+
"train_runtime": 1315.8778,
|
| 64 |
+
"train_samples_per_second": 12.936,
|
| 65 |
+
"train_steps_per_second": 3.237
|
| 66 |
+
}
|
| 67 |
+
],
|
| 68 |
+
"max_steps": 4260,
|
| 69 |
+
"num_train_epochs": 6,
|
| 70 |
+
"total_flos": 72510721228800.0,
|
| 71 |
+
"trial_name": null,
|
| 72 |
+
"trial_params": null
|
| 73 |
+
}
|