add model files
Browse files- config.json +47 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +44 -0
- tokenizer_config.json +54 -0
- trainer_state.json +592 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./checkpoint-57102/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"TaatikModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 57344,
|
| 8 |
+
"downsampling_rate": 4,
|
| 9 |
+
"eos_token_id": 57345,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5",
|
| 20 |
+
"6": "LABEL_6"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"LABEL_0": 0,
|
| 26 |
+
"LABEL_1": 1,
|
| 27 |
+
"LABEL_2": 2,
|
| 28 |
+
"LABEL_3": 3,
|
| 29 |
+
"LABEL_4": 4,
|
| 30 |
+
"LABEL_5": 5,
|
| 31 |
+
"LABEL_6": 6
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-12,
|
| 34 |
+
"local_transformer_stride": 128,
|
| 35 |
+
"max_position_embeddings": 16384,
|
| 36 |
+
"model_type": "canine",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_hash_buckets": 16384,
|
| 39 |
+
"num_hash_functions": 8,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"pad_token_id": 0,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.29.2",
|
| 44 |
+
"type_vocab_size": 16,
|
| 45 |
+
"upsampling_kernel_size": 4,
|
| 46 |
+
"use_cache": true
|
| 47 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dd8cc4a5698f1d45b2423b8651687249a0118b7f3ebd299a01b88b699f95b96
|
| 3 |
+
size 528570097
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9e97b92004128ef13af1ba63ee0b6bdf2c13202ddb3a64fd68a085b6005909e
|
| 3 |
+
size 14575
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "\u0000",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"clean_up_tokenization_spaces": true,
|
| 12 |
+
"cls_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"__type": "AddedToken",
|
| 22 |
+
"content": "",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"model_max_length": 2048,
|
| 37 |
+
"pad_token": {
|
| 38 |
+
"__type": "AddedToken",
|
| 39 |
+
"content": "\u0000",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
"sep_token": {
|
| 46 |
+
"__type": "AddedToken",
|
| 47 |
+
"content": "",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
},
|
| 53 |
+
"tokenizer_class": "CanineTokenizer"
|
| 54 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,592 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.999912914743534,
|
| 5 |
+
"global_step": 31578,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.17,
|
| 12 |
+
"learning_rate": 4.9419279907084783e-05,
|
| 13 |
+
"loss": 0.0381,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.35,
|
| 18 |
+
"learning_rate": 4.883855981416957e-05,
|
| 19 |
+
"loss": 0.0241,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.52,
|
| 24 |
+
"learning_rate": 4.825783972125435e-05,
|
| 25 |
+
"loss": 0.022,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.7,
|
| 30 |
+
"learning_rate": 4.767711962833915e-05,
|
| 31 |
+
"loss": 0.0207,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.87,
|
| 36 |
+
"learning_rate": 4.709639953542393e-05,
|
| 37 |
+
"loss": 0.0199,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_accuracy": 0.9726582157682948,
|
| 43 |
+
"eval_f1_HIRIQ": 0.7791055764551668,
|
| 44 |
+
"eval_f1_HOLAM": 0.6713693875265927,
|
| 45 |
+
"eval_f1_KUBUTZ": 0.7119160348309771,
|
| 46 |
+
"eval_f1_PATACH": 0.851339663936741,
|
| 47 |
+
"eval_f1_SHADDA": 0.8292565235143462,
|
| 48 |
+
"eval_f1_SHVA": 0.8089031685917613,
|
| 49 |
+
"eval_f1_TSERE": 0.7485289696344972,
|
| 50 |
+
"eval_loss": 0.013756499625742435,
|
| 51 |
+
"eval_macro_f1": 0.7714884749271546,
|
| 52 |
+
"eval_micro_f1": 0.8119978846741942,
|
| 53 |
+
"eval_runtime": 51.0176,
|
| 54 |
+
"eval_samples_per_second": 750.232,
|
| 55 |
+
"eval_steps_per_second": 7.507,
|
| 56 |
+
"step": 2870
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.05,
|
| 60 |
+
"learning_rate": 4.6515679442508716e-05,
|
| 61 |
+
"loss": 0.0189,
|
| 62 |
+
"step": 3000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.22,
|
| 66 |
+
"learning_rate": 4.59349593495935e-05,
|
| 67 |
+
"loss": 0.0177,
|
| 68 |
+
"step": 3500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.39,
|
| 72 |
+
"learning_rate": 4.5354239256678285e-05,
|
| 73 |
+
"loss": 0.0174,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.57,
|
| 78 |
+
"learning_rate": 4.4773519163763066e-05,
|
| 79 |
+
"loss": 0.0172,
|
| 80 |
+
"step": 4500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.74,
|
| 84 |
+
"learning_rate": 4.4192799070847854e-05,
|
| 85 |
+
"loss": 0.0167,
|
| 86 |
+
"step": 5000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.92,
|
| 90 |
+
"learning_rate": 4.361207897793264e-05,
|
| 91 |
+
"loss": 0.0166,
|
| 92 |
+
"step": 5500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.0,
|
| 96 |
+
"eval_accuracy": 0.9761089815978242,
|
| 97 |
+
"eval_f1_HIRIQ": 0.8106474124231328,
|
| 98 |
+
"eval_f1_HOLAM": 0.7086283185840708,
|
| 99 |
+
"eval_f1_KUBUTZ": 0.7472128945601075,
|
| 100 |
+
"eval_f1_PATACH": 0.8701410253039187,
|
| 101 |
+
"eval_f1_SHADDA": 0.8522099185169709,
|
| 102 |
+
"eval_f1_SHVA": 0.8329891346774823,
|
| 103 |
+
"eval_f1_TSERE": 0.7836281031964952,
|
| 104 |
+
"eval_loss": 0.012357393279671669,
|
| 105 |
+
"eval_macro_f1": 0.8007795438945969,
|
| 106 |
+
"eval_micro_f1": 0.8363289062525998,
|
| 107 |
+
"eval_runtime": 52.8127,
|
| 108 |
+
"eval_samples_per_second": 724.731,
|
| 109 |
+
"eval_steps_per_second": 7.252,
|
| 110 |
+
"step": 5741
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.09,
|
| 114 |
+
"learning_rate": 4.303135888501742e-05,
|
| 115 |
+
"loss": 0.0157,
|
| 116 |
+
"step": 6000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.26,
|
| 120 |
+
"learning_rate": 4.245063879210221e-05,
|
| 121 |
+
"loss": 0.0151,
|
| 122 |
+
"step": 6500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.44,
|
| 126 |
+
"learning_rate": 4.186991869918699e-05,
|
| 127 |
+
"loss": 0.015,
|
| 128 |
+
"step": 7000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.61,
|
| 132 |
+
"learning_rate": 4.128919860627178e-05,
|
| 133 |
+
"loss": 0.0148,
|
| 134 |
+
"step": 7500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.79,
|
| 138 |
+
"learning_rate": 4.070847851335656e-05,
|
| 139 |
+
"loss": 0.0148,
|
| 140 |
+
"step": 8000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.96,
|
| 144 |
+
"learning_rate": 4.012775842044135e-05,
|
| 145 |
+
"loss": 0.0147,
|
| 146 |
+
"step": 8500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.0,
|
| 150 |
+
"eval_accuracy": 0.9780662605569959,
|
| 151 |
+
"eval_f1_HIRIQ": 0.8294876571557304,
|
| 152 |
+
"eval_f1_HOLAM": 0.7245056654076871,
|
| 153 |
+
"eval_f1_KUBUTZ": 0.7711184824965379,
|
| 154 |
+
"eval_f1_PATACH": 0.8810396563640023,
|
| 155 |
+
"eval_f1_SHADDA": 0.8664105216491798,
|
| 156 |
+
"eval_f1_SHVA": 0.8441380510188548,
|
| 157 |
+
"eval_f1_TSERE": 0.7970168612191959,
|
| 158 |
+
"eval_loss": 0.011536195874214172,
|
| 159 |
+
"eval_macro_f1": 0.8162452707587411,
|
| 160 |
+
"eval_micro_f1": 0.8498705967528521,
|
| 161 |
+
"eval_runtime": 54.0777,
|
| 162 |
+
"eval_samples_per_second": 707.778,
|
| 163 |
+
"eval_steps_per_second": 7.082,
|
| 164 |
+
"step": 8612
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.14,
|
| 168 |
+
"learning_rate": 3.9547038327526136e-05,
|
| 169 |
+
"loss": 0.0137,
|
| 170 |
+
"step": 9000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.31,
|
| 174 |
+
"learning_rate": 3.8966318234610924e-05,
|
| 175 |
+
"loss": 0.0134,
|
| 176 |
+
"step": 9500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.48,
|
| 180 |
+
"learning_rate": 3.8385598141695705e-05,
|
| 181 |
+
"loss": 0.0135,
|
| 182 |
+
"step": 10000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.66,
|
| 186 |
+
"learning_rate": 3.780487804878049e-05,
|
| 187 |
+
"loss": 0.0135,
|
| 188 |
+
"step": 10500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.83,
|
| 192 |
+
"learning_rate": 3.7224157955865274e-05,
|
| 193 |
+
"loss": 0.0132,
|
| 194 |
+
"step": 11000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.0,
|
| 198 |
+
"eval_accuracy": 0.9792273312868799,
|
| 199 |
+
"eval_f1_HIRIQ": 0.8373507327062703,
|
| 200 |
+
"eval_f1_HOLAM": 0.7442917433178227,
|
| 201 |
+
"eval_f1_KUBUTZ": 0.7827533265097235,
|
| 202 |
+
"eval_f1_PATACH": 0.8867928661237257,
|
| 203 |
+
"eval_f1_SHADDA": 0.8725204092940786,
|
| 204 |
+
"eval_f1_SHVA": 0.8508812530764879,
|
| 205 |
+
"eval_f1_TSERE": 0.801735428945645,
|
| 206 |
+
"eval_loss": 0.010950990952551365,
|
| 207 |
+
"eval_macro_f1": 0.8251893942819649,
|
| 208 |
+
"eval_micro_f1": 0.8567964095958783,
|
| 209 |
+
"eval_runtime": 52.4162,
|
| 210 |
+
"eval_samples_per_second": 730.213,
|
| 211 |
+
"eval_steps_per_second": 7.307,
|
| 212 |
+
"step": 11483
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.01,
|
| 216 |
+
"learning_rate": 3.664343786295006e-05,
|
| 217 |
+
"loss": 0.0131,
|
| 218 |
+
"step": 11500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.18,
|
| 222 |
+
"learning_rate": 3.606271777003484e-05,
|
| 223 |
+
"loss": 0.0122,
|
| 224 |
+
"step": 12000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.35,
|
| 228 |
+
"learning_rate": 3.548199767711963e-05,
|
| 229 |
+
"loss": 0.0122,
|
| 230 |
+
"step": 12500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.53,
|
| 234 |
+
"learning_rate": 3.490127758420442e-05,
|
| 235 |
+
"loss": 0.0123,
|
| 236 |
+
"step": 13000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.7,
|
| 240 |
+
"learning_rate": 3.43205574912892e-05,
|
| 241 |
+
"loss": 0.0122,
|
| 242 |
+
"step": 13500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.88,
|
| 246 |
+
"learning_rate": 3.373983739837399e-05,
|
| 247 |
+
"loss": 0.0122,
|
| 248 |
+
"step": 14000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.0,
|
| 252 |
+
"eval_accuracy": 0.9799653269288884,
|
| 253 |
+
"eval_f1_HIRIQ": 0.8439961236895427,
|
| 254 |
+
"eval_f1_HOLAM": 0.7499999999999999,
|
| 255 |
+
"eval_f1_KUBUTZ": 0.7890396727485228,
|
| 256 |
+
"eval_f1_PATACH": 0.8902453557194496,
|
| 257 |
+
"eval_f1_SHADDA": 0.8791103582869978,
|
| 258 |
+
"eval_f1_SHVA": 0.8568982423275623,
|
| 259 |
+
"eval_f1_TSERE": 0.8086938522045125,
|
| 260 |
+
"eval_loss": 0.010681645944714546,
|
| 261 |
+
"eval_macro_f1": 0.8311405149966554,
|
| 262 |
+
"eval_micro_f1": 0.8620291101643662,
|
| 263 |
+
"eval_runtime": 49.3354,
|
| 264 |
+
"eval_samples_per_second": 775.812,
|
| 265 |
+
"eval_steps_per_second": 7.763,
|
| 266 |
+
"step": 14353
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.05,
|
| 270 |
+
"learning_rate": 3.315911730545877e-05,
|
| 271 |
+
"loss": 0.012,
|
| 272 |
+
"step": 14500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.23,
|
| 276 |
+
"learning_rate": 3.2578397212543556e-05,
|
| 277 |
+
"loss": 0.011,
|
| 278 |
+
"step": 15000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.4,
|
| 282 |
+
"learning_rate": 3.199767711962834e-05,
|
| 283 |
+
"loss": 0.0114,
|
| 284 |
+
"step": 15500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.57,
|
| 288 |
+
"learning_rate": 3.1416957026713125e-05,
|
| 289 |
+
"loss": 0.0112,
|
| 290 |
+
"step": 16000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.75,
|
| 294 |
+
"learning_rate": 3.083623693379791e-05,
|
| 295 |
+
"loss": 0.0112,
|
| 296 |
+
"step": 16500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 5.92,
|
| 300 |
+
"learning_rate": 3.0255516840882698e-05,
|
| 301 |
+
"loss": 0.0112,
|
| 302 |
+
"step": 17000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.0,
|
| 306 |
+
"eval_accuracy": 0.9805248675902215,
|
| 307 |
+
"eval_f1_HIRIQ": 0.8487574675668987,
|
| 308 |
+
"eval_f1_HOLAM": 0.7595126122274476,
|
| 309 |
+
"eval_f1_KUBUTZ": 0.797991035951556,
|
| 310 |
+
"eval_f1_PATACH": 0.8928041018387551,
|
| 311 |
+
"eval_f1_SHADDA": 0.8846275811897255,
|
| 312 |
+
"eval_f1_SHVA": 0.8607482938928253,
|
| 313 |
+
"eval_f1_TSERE": 0.8122762990085161,
|
| 314 |
+
"eval_loss": 0.010463288053870201,
|
| 315 |
+
"eval_macro_f1": 0.8366739130965322,
|
| 316 |
+
"eval_micro_f1": 0.8659091900525827,
|
| 317 |
+
"eval_runtime": 49.2152,
|
| 318 |
+
"eval_samples_per_second": 777.707,
|
| 319 |
+
"eval_steps_per_second": 7.782,
|
| 320 |
+
"step": 17224
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.1,
|
| 324 |
+
"learning_rate": 2.9674796747967482e-05,
|
| 325 |
+
"loss": 0.0107,
|
| 326 |
+
"step": 17500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.27,
|
| 330 |
+
"learning_rate": 2.9094076655052267e-05,
|
| 331 |
+
"loss": 0.0105,
|
| 332 |
+
"step": 18000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.44,
|
| 336 |
+
"learning_rate": 2.851335656213705e-05,
|
| 337 |
+
"loss": 0.0103,
|
| 338 |
+
"step": 18500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.62,
|
| 342 |
+
"learning_rate": 2.7932636469221835e-05,
|
| 343 |
+
"loss": 0.0106,
|
| 344 |
+
"step": 19000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.79,
|
| 348 |
+
"learning_rate": 2.735191637630662e-05,
|
| 349 |
+
"loss": 0.0105,
|
| 350 |
+
"step": 19500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.97,
|
| 354 |
+
"learning_rate": 2.6771196283391408e-05,
|
| 355 |
+
"loss": 0.0104,
|
| 356 |
+
"step": 20000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 7.0,
|
| 360 |
+
"eval_accuracy": 0.9811321234870294,
|
| 361 |
+
"eval_f1_HIRIQ": 0.8550038223948401,
|
| 362 |
+
"eval_f1_HOLAM": 0.763222830168437,
|
| 363 |
+
"eval_f1_KUBUTZ": 0.8037383177570094,
|
| 364 |
+
"eval_f1_PATACH": 0.8963010344751529,
|
| 365 |
+
"eval_f1_SHADDA": 0.8854757929883139,
|
| 366 |
+
"eval_f1_SHVA": 0.8649184871804224,
|
| 367 |
+
"eval_f1_TSERE": 0.8171559407964675,
|
| 368 |
+
"eval_loss": 0.010495145805180073,
|
| 369 |
+
"eval_macro_f1": 0.8408308893943776,
|
| 370 |
+
"eval_micro_f1": 0.8700826091477137,
|
| 371 |
+
"eval_runtime": 52.1218,
|
| 372 |
+
"eval_samples_per_second": 734.337,
|
| 373 |
+
"eval_steps_per_second": 7.348,
|
| 374 |
+
"step": 20095
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 7.14,
|
| 378 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 379 |
+
"loss": 0.0098,
|
| 380 |
+
"step": 20500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.32,
|
| 384 |
+
"learning_rate": 2.5609756097560977e-05,
|
| 385 |
+
"loss": 0.0097,
|
| 386 |
+
"step": 21000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 7.49,
|
| 390 |
+
"learning_rate": 2.502903600464576e-05,
|
| 391 |
+
"loss": 0.0097,
|
| 392 |
+
"step": 21500
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 7.66,
|
| 396 |
+
"learning_rate": 2.4448315911730546e-05,
|
| 397 |
+
"loss": 0.0098,
|
| 398 |
+
"step": 22000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 7.84,
|
| 402 |
+
"learning_rate": 2.3867595818815333e-05,
|
| 403 |
+
"loss": 0.0097,
|
| 404 |
+
"step": 22500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 8.0,
|
| 408 |
+
"eval_accuracy": 0.981536112480715,
|
| 409 |
+
"eval_f1_HIRIQ": 0.8594682202461781,
|
| 410 |
+
"eval_f1_HOLAM": 0.7635878626208735,
|
| 411 |
+
"eval_f1_KUBUTZ": 0.8044461430664374,
|
| 412 |
+
"eval_f1_PATACH": 0.8982397971622214,
|
| 413 |
+
"eval_f1_SHADDA": 0.888189855746859,
|
| 414 |
+
"eval_f1_SHVA": 0.8671149394978173,
|
| 415 |
+
"eval_f1_TSERE": 0.8201351021404737,
|
| 416 |
+
"eval_loss": 0.010434958152472973,
|
| 417 |
+
"eval_macro_f1": 0.8430259886401229,
|
| 418 |
+
"eval_micro_f1": 0.8725397588417411,
|
| 419 |
+
"eval_runtime": 50.6576,
|
| 420 |
+
"eval_samples_per_second": 755.562,
|
| 421 |
+
"eval_steps_per_second": 7.561,
|
| 422 |
+
"step": 22966
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 8.01,
|
| 426 |
+
"learning_rate": 2.3286875725900118e-05,
|
| 427 |
+
"loss": 0.0096,
|
| 428 |
+
"step": 23000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 8.19,
|
| 432 |
+
"learning_rate": 2.2706155632984902e-05,
|
| 433 |
+
"loss": 0.009,
|
| 434 |
+
"step": 23500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.36,
|
| 438 |
+
"learning_rate": 2.2125435540069687e-05,
|
| 439 |
+
"loss": 0.0091,
|
| 440 |
+
"step": 24000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.53,
|
| 444 |
+
"learning_rate": 2.1544715447154475e-05,
|
| 445 |
+
"loss": 0.0091,
|
| 446 |
+
"step": 24500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.71,
|
| 450 |
+
"learning_rate": 2.096399535423926e-05,
|
| 451 |
+
"loss": 0.0092,
|
| 452 |
+
"step": 25000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.88,
|
| 456 |
+
"learning_rate": 2.038327526132404e-05,
|
| 457 |
+
"loss": 0.0091,
|
| 458 |
+
"step": 25500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 9.0,
|
| 462 |
+
"eval_accuracy": 0.9816429946081784,
|
| 463 |
+
"eval_f1_HIRIQ": 0.8617756604590732,
|
| 464 |
+
"eval_f1_HOLAM": 0.7760372565622354,
|
| 465 |
+
"eval_f1_KUBUTZ": 0.8087252634284247,
|
| 466 |
+
"eval_f1_PATACH": 0.8981484778351434,
|
| 467 |
+
"eval_f1_SHADDA": 0.8896060289509028,
|
| 468 |
+
"eval_f1_SHVA": 0.8676933023775238,
|
| 469 |
+
"eval_f1_TSERE": 0.8195844976309076,
|
| 470 |
+
"eval_loss": 0.010549969039857388,
|
| 471 |
+
"eval_macro_f1": 0.8459386410348871,
|
| 472 |
+
"eval_micro_f1": 0.8734815959940515,
|
| 473 |
+
"eval_runtime": 50.289,
|
| 474 |
+
"eval_samples_per_second": 761.101,
|
| 475 |
+
"eval_steps_per_second": 7.616,
|
| 476 |
+
"step": 25836
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 9.06,
|
| 480 |
+
"learning_rate": 1.9802555168408828e-05,
|
| 481 |
+
"loss": 0.0088,
|
| 482 |
+
"step": 26000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.23,
|
| 486 |
+
"learning_rate": 1.9221835075493612e-05,
|
| 487 |
+
"loss": 0.0085,
|
| 488 |
+
"step": 26500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 9.41,
|
| 492 |
+
"learning_rate": 1.8641114982578397e-05,
|
| 493 |
+
"loss": 0.0086,
|
| 494 |
+
"step": 27000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 9.58,
|
| 498 |
+
"learning_rate": 1.806039488966318e-05,
|
| 499 |
+
"loss": 0.0085,
|
| 500 |
+
"step": 27500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 9.75,
|
| 504 |
+
"learning_rate": 1.747967479674797e-05,
|
| 505 |
+
"loss": 0.0086,
|
| 506 |
+
"step": 28000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 9.93,
|
| 510 |
+
"learning_rate": 1.6898954703832754e-05,
|
| 511 |
+
"loss": 0.0086,
|
| 512 |
+
"step": 28500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 10.0,
|
| 516 |
+
"eval_accuracy": 0.9820323509296518,
|
| 517 |
+
"eval_f1_HIRIQ": 0.8644184686296934,
|
| 518 |
+
"eval_f1_HOLAM": 0.7807301793043854,
|
| 519 |
+
"eval_f1_KUBUTZ": 0.8107445035070613,
|
| 520 |
+
"eval_f1_PATACH": 0.9007614706453949,
|
| 521 |
+
"eval_f1_SHADDA": 0.8914874936954775,
|
| 522 |
+
"eval_f1_SHVA": 0.8700223746362294,
|
| 523 |
+
"eval_f1_TSERE": 0.8237858288440186,
|
| 524 |
+
"eval_loss": 0.010514745488762856,
|
| 525 |
+
"eval_macro_f1": 0.8488500456088944,
|
| 526 |
+
"eval_micro_f1": 0.876108330623615,
|
| 527 |
+
"eval_runtime": 51.4328,
|
| 528 |
+
"eval_samples_per_second": 744.175,
|
| 529 |
+
"eval_steps_per_second": 7.447,
|
| 530 |
+
"step": 28707
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 10.1,
|
| 534 |
+
"learning_rate": 1.6318234610917538e-05,
|
| 535 |
+
"loss": 0.0083,
|
| 536 |
+
"step": 29000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 10.28,
|
| 540 |
+
"learning_rate": 1.5737514518002326e-05,
|
| 541 |
+
"loss": 0.008,
|
| 542 |
+
"step": 29500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 10.45,
|
| 546 |
+
"learning_rate": 1.5156794425087109e-05,
|
| 547 |
+
"loss": 0.0082,
|
| 548 |
+
"step": 30000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 10.62,
|
| 552 |
+
"learning_rate": 1.4576074332171893e-05,
|
| 553 |
+
"loss": 0.0081,
|
| 554 |
+
"step": 30500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 10.8,
|
| 558 |
+
"learning_rate": 1.3995354239256678e-05,
|
| 559 |
+
"loss": 0.0081,
|
| 560 |
+
"step": 31000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 10.97,
|
| 564 |
+
"learning_rate": 1.3414634146341466e-05,
|
| 565 |
+
"loss": 0.0081,
|
| 566 |
+
"step": 31500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 11.0,
|
| 570 |
+
"eval_accuracy": 0.9822652012787683,
|
| 571 |
+
"eval_f1_HIRIQ": 0.8650168041552093,
|
| 572 |
+
"eval_f1_HOLAM": 0.7809975223526877,
|
| 573 |
+
"eval_f1_KUBUTZ": 0.8156180840973759,
|
| 574 |
+
"eval_f1_PATACH": 0.9017915187001648,
|
| 575 |
+
"eval_f1_SHADDA": 0.893456266013353,
|
| 576 |
+
"eval_f1_SHVA": 0.8708873379860418,
|
| 577 |
+
"eval_f1_TSERE": 0.824460194494808,
|
| 578 |
+
"eval_loss": 0.010741644538939,
|
| 579 |
+
"eval_macro_f1": 0.85031824682852,
|
| 580 |
+
"eval_micro_f1": 0.8772879261954959,
|
| 581 |
+
"eval_runtime": 49.6631,
|
| 582 |
+
"eval_samples_per_second": 770.693,
|
| 583 |
+
"eval_steps_per_second": 7.712,
|
| 584 |
+
"step": 31578
|
| 585 |
+
}
|
| 586 |
+
],
|
| 587 |
+
"max_steps": 43050,
|
| 588 |
+
"num_train_epochs": 15,
|
| 589 |
+
"total_flos": 1.540842233529006e+17,
|
| 590 |
+
"trial_name": null,
|
| 591 |
+
"trial_params": null
|
| 592 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0d052a377ad936604b1eb20f528c46aa17e381e8691df270f7d13eaa4031809
|
| 3 |
+
size 4027
|