roBERTa model finetuned with sst2
Browse files- all_results.json +15 -0
- config.json +36 -0
- eval_results.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +64 -0
- train_results.json +8 -0
- trainer_state.json +417 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.1,
|
| 3 |
+
"eval_accuracy": 0.8070865869522095,
|
| 4 |
+
"eval_f1": 0.7999999999999999,
|
| 5 |
+
"eval_loss": 0.593163251876831,
|
| 6 |
+
"eval_runtime": 0.8855,
|
| 7 |
+
"eval_samples": 508,
|
| 8 |
+
"eval_samples_per_second": 573.715,
|
| 9 |
+
"eval_steps_per_second": 72.279,
|
| 10 |
+
"train_loss": 0.14836265951395033,
|
| 11 |
+
"train_runtime": 2029.2795,
|
| 12 |
+
"train_samples": 50528,
|
| 13 |
+
"train_samples_per_second": 248.995,
|
| 14 |
+
"train_steps_per_second": 3.893
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/bel3/content/model_folder/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 0,
|
| 15 |
+
"1": 1
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "roberta",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 6,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.26.1",
|
| 33 |
+
"type_vocab_size": 1,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 52000
|
| 36 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.1,
|
| 3 |
+
"eval_accuracy": 0.8070865869522095,
|
| 4 |
+
"eval_f1": 0.7999999999999999,
|
| 5 |
+
"eval_loss": 0.593163251876831,
|
| 6 |
+
"eval_runtime": 0.8855,
|
| 7 |
+
"eval_samples": 508,
|
| 8 |
+
"eval_samples_per_second": 573.715,
|
| 9 |
+
"eval_steps_per_second": 72.279
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00aa7063dd62f4f8662fbc03a574fc46f20d97322ec46e6be795790f93ae01f2
|
| 3 |
+
size 333848685
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"cls_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"__type": "AddedToken",
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"errors": "replace",
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<mask>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"name_or_path": "/home/bel3/content/model_folder/",
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"sep_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "</s>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"special_tokens_map_file": null,
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"unk_token": {
|
| 57 |
+
"__type": "AddedToken",
|
| 58 |
+
"content": "<unk>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": true,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false
|
| 63 |
+
}
|
| 64 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.1,
|
| 3 |
+
"train_loss": 0.14836265951395033,
|
| 4 |
+
"train_runtime": 2029.2795,
|
| 5 |
+
"train_samples": 50528,
|
| 6 |
+
"train_samples_per_second": 248.995,
|
| 7 |
+
"train_steps_per_second": 3.893
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7999999999999999,
|
| 3 |
+
"best_model_checkpoint": "/home/bel3/content/model_folder//finetune/sst2/checkpoint-2000",
|
| 4 |
+
"epoch": 8.10126582278481,
|
| 5 |
+
"global_step": 6400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.25,
|
| 12 |
+
"eval_accuracy": 0.7637795209884644,
|
| 13 |
+
"eval_f1": 0.7894736842105263,
|
| 14 |
+
"eval_loss": 0.5017877817153931,
|
| 15 |
+
"eval_runtime": 0.8927,
|
| 16 |
+
"eval_samples_per_second": 569.063,
|
| 17 |
+
"eval_steps_per_second": 71.693,
|
| 18 |
+
"step": 200
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.51,
|
| 22 |
+
"eval_accuracy": 0.8070865869522095,
|
| 23 |
+
"eval_f1": 0.8178438661710037,
|
| 24 |
+
"eval_loss": 0.4368048310279846,
|
| 25 |
+
"eval_runtime": 0.896,
|
| 26 |
+
"eval_samples_per_second": 566.985,
|
| 27 |
+
"eval_steps_per_second": 71.431,
|
| 28 |
+
"step": 400
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.63,
|
| 32 |
+
"learning_rate": 4.683544303797468e-05,
|
| 33 |
+
"loss": 0.4948,
|
| 34 |
+
"step": 500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.76,
|
| 38 |
+
"eval_accuracy": 0.789370059967041,
|
| 39 |
+
"eval_f1": 0.7906066536203523,
|
| 40 |
+
"eval_loss": 0.45398545265197754,
|
| 41 |
+
"eval_runtime": 0.895,
|
| 42 |
+
"eval_samples_per_second": 567.578,
|
| 43 |
+
"eval_steps_per_second": 71.506,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.01,
|
| 48 |
+
"eval_accuracy": 0.8011810779571533,
|
| 49 |
+
"eval_f1": 0.7908902691511387,
|
| 50 |
+
"eval_loss": 0.44997021555900574,
|
| 51 |
+
"eval_runtime": 0.9042,
|
| 52 |
+
"eval_samples_per_second": 561.806,
|
| 53 |
+
"eval_steps_per_second": 70.779,
|
| 54 |
+
"step": 800
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.27,
|
| 58 |
+
"learning_rate": 4.367088607594937e-05,
|
| 59 |
+
"loss": 0.3027,
|
| 60 |
+
"step": 1000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.27,
|
| 64 |
+
"eval_accuracy": 0.8129921555519104,
|
| 65 |
+
"eval_f1": 0.8155339805825244,
|
| 66 |
+
"eval_loss": 0.4525600075721741,
|
| 67 |
+
"eval_runtime": 0.833,
|
| 68 |
+
"eval_samples_per_second": 609.864,
|
| 69 |
+
"eval_steps_per_second": 76.833,
|
| 70 |
+
"step": 1000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.52,
|
| 74 |
+
"eval_accuracy": 0.8208661675453186,
|
| 75 |
+
"eval_f1": 0.8253358925143954,
|
| 76 |
+
"eval_loss": 0.4560699462890625,
|
| 77 |
+
"eval_runtime": 0.8459,
|
| 78 |
+
"eval_samples_per_second": 600.52,
|
| 79 |
+
"eval_steps_per_second": 75.656,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.77,
|
| 84 |
+
"eval_accuracy": 0.8149606585502625,
|
| 85 |
+
"eval_f1": 0.812,
|
| 86 |
+
"eval_loss": 0.4809434413909912,
|
| 87 |
+
"eval_runtime": 0.8476,
|
| 88 |
+
"eval_samples_per_second": 599.306,
|
| 89 |
+
"eval_steps_per_second": 75.503,
|
| 90 |
+
"step": 1400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.9,
|
| 94 |
+
"learning_rate": 4.050632911392405e-05,
|
| 95 |
+
"loss": 0.236,
|
| 96 |
+
"step": 1500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.03,
|
| 100 |
+
"eval_accuracy": 0.8169291615486145,
|
| 101 |
+
"eval_f1": 0.8228571428571428,
|
| 102 |
+
"eval_loss": 0.6252030730247498,
|
| 103 |
+
"eval_runtime": 0.9277,
|
| 104 |
+
"eval_samples_per_second": 547.599,
|
| 105 |
+
"eval_steps_per_second": 68.989,
|
| 106 |
+
"step": 1600
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.28,
|
| 110 |
+
"eval_accuracy": 0.8149606585502625,
|
| 111 |
+
"eval_f1": 0.8142292490118577,
|
| 112 |
+
"eval_loss": 0.6088564395904541,
|
| 113 |
+
"eval_runtime": 0.8559,
|
| 114 |
+
"eval_samples_per_second": 593.542,
|
| 115 |
+
"eval_steps_per_second": 74.777,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.53,
|
| 120 |
+
"learning_rate": 3.7341772151898736e-05,
|
| 121 |
+
"loss": 0.1743,
|
| 122 |
+
"step": 2000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.53,
|
| 126 |
+
"eval_accuracy": 0.8070865869522095,
|
| 127 |
+
"eval_f1": 0.7999999999999999,
|
| 128 |
+
"eval_loss": 0.593163251876831,
|
| 129 |
+
"eval_runtime": 0.8297,
|
| 130 |
+
"eval_samples_per_second": 612.294,
|
| 131 |
+
"eval_steps_per_second": 77.139,
|
| 132 |
+
"step": 2000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.78,
|
| 136 |
+
"eval_accuracy": 0.8090550899505615,
|
| 137 |
+
"eval_f1": 0.7991718426501037,
|
| 138 |
+
"eval_loss": 0.5563398599624634,
|
| 139 |
+
"eval_runtime": 0.8844,
|
| 140 |
+
"eval_samples_per_second": 574.387,
|
| 141 |
+
"eval_steps_per_second": 72.364,
|
| 142 |
+
"step": 2200
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.04,
|
| 146 |
+
"eval_accuracy": 0.7972440719604492,
|
| 147 |
+
"eval_f1": 0.8052930056710774,
|
| 148 |
+
"eval_loss": 0.5898112058639526,
|
| 149 |
+
"eval_runtime": 0.9275,
|
| 150 |
+
"eval_samples_per_second": 547.695,
|
| 151 |
+
"eval_steps_per_second": 69.001,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.16,
|
| 156 |
+
"learning_rate": 3.4177215189873416e-05,
|
| 157 |
+
"loss": 0.1599,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.29,
|
| 162 |
+
"eval_accuracy": 0.8228346705436707,
|
| 163 |
+
"eval_f1": 0.8228346456692914,
|
| 164 |
+
"eval_loss": 0.538675844669342,
|
| 165 |
+
"eval_runtime": 0.9213,
|
| 166 |
+
"eval_samples_per_second": 551.421,
|
| 167 |
+
"eval_steps_per_second": 69.47,
|
| 168 |
+
"step": 2600
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.54,
|
| 172 |
+
"eval_accuracy": 0.8110235929489136,
|
| 173 |
+
"eval_f1": 0.8087649402390438,
|
| 174 |
+
"eval_loss": 0.5058029890060425,
|
| 175 |
+
"eval_runtime": 0.9251,
|
| 176 |
+
"eval_samples_per_second": 549.151,
|
| 177 |
+
"eval_steps_per_second": 69.184,
|
| 178 |
+
"step": 2800
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.8,
|
| 182 |
+
"learning_rate": 3.10126582278481e-05,
|
| 183 |
+
"loss": 0.1218,
|
| 184 |
+
"step": 3000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.8,
|
| 188 |
+
"eval_accuracy": 0.8248031735420227,
|
| 189 |
+
"eval_f1": 0.8216432865731464,
|
| 190 |
+
"eval_loss": 0.6525737047195435,
|
| 191 |
+
"eval_runtime": 0.8811,
|
| 192 |
+
"eval_samples_per_second": 576.522,
|
| 193 |
+
"eval_steps_per_second": 72.633,
|
| 194 |
+
"step": 3000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.05,
|
| 198 |
+
"eval_accuracy": 0.8110235929489136,
|
| 199 |
+
"eval_f1": 0.8102766798418972,
|
| 200 |
+
"eval_loss": 0.8057999610900879,
|
| 201 |
+
"eval_runtime": 0.8465,
|
| 202 |
+
"eval_samples_per_second": 600.11,
|
| 203 |
+
"eval_steps_per_second": 75.604,
|
| 204 |
+
"step": 3200
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.3,
|
| 208 |
+
"eval_accuracy": 0.8110235929489136,
|
| 209 |
+
"eval_f1": 0.8032786885245902,
|
| 210 |
+
"eval_loss": 0.7197728753089905,
|
| 211 |
+
"eval_runtime": 0.8474,
|
| 212 |
+
"eval_samples_per_second": 599.485,
|
| 213 |
+
"eval_steps_per_second": 75.526,
|
| 214 |
+
"step": 3400
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 4.43,
|
| 218 |
+
"learning_rate": 2.7848101265822786e-05,
|
| 219 |
+
"loss": 0.0955,
|
| 220 |
+
"step": 3500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.56,
|
| 224 |
+
"eval_accuracy": 0.8031495809555054,
|
| 225 |
+
"eval_f1": 0.7967479674796747,
|
| 226 |
+
"eval_loss": 0.7408320903778076,
|
| 227 |
+
"eval_runtime": 0.8491,
|
| 228 |
+
"eval_samples_per_second": 598.276,
|
| 229 |
+
"eval_steps_per_second": 75.373,
|
| 230 |
+
"step": 3600
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.81,
|
| 234 |
+
"eval_accuracy": 0.8011810779571533,
|
| 235 |
+
"eval_f1": 0.8112149532710279,
|
| 236 |
+
"eval_loss": 0.7727562785148621,
|
| 237 |
+
"eval_runtime": 0.8979,
|
| 238 |
+
"eval_samples_per_second": 565.791,
|
| 239 |
+
"eval_steps_per_second": 71.281,
|
| 240 |
+
"step": 3800
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.06,
|
| 244 |
+
"learning_rate": 2.468354430379747e-05,
|
| 245 |
+
"loss": 0.0858,
|
| 246 |
+
"step": 4000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.06,
|
| 250 |
+
"eval_accuracy": 0.8051180839538574,
|
| 251 |
+
"eval_f1": 0.800804828973843,
|
| 252 |
+
"eval_loss": 0.8653830885887146,
|
| 253 |
+
"eval_runtime": 0.8947,
|
| 254 |
+
"eval_samples_per_second": 567.8,
|
| 255 |
+
"eval_steps_per_second": 71.534,
|
| 256 |
+
"step": 4000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 5.32,
|
| 260 |
+
"eval_accuracy": 0.789370059967041,
|
| 261 |
+
"eval_f1": 0.8065099457504521,
|
| 262 |
+
"eval_loss": 0.9238587021827698,
|
| 263 |
+
"eval_runtime": 0.8912,
|
| 264 |
+
"eval_samples_per_second": 570.005,
|
| 265 |
+
"eval_steps_per_second": 71.812,
|
| 266 |
+
"step": 4200
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.57,
|
| 270 |
+
"eval_accuracy": 0.7814960479736328,
|
| 271 |
+
"eval_f1": 0.7940630797773653,
|
| 272 |
+
"eval_loss": 0.8553095459938049,
|
| 273 |
+
"eval_runtime": 0.8957,
|
| 274 |
+
"eval_samples_per_second": 567.124,
|
| 275 |
+
"eval_steps_per_second": 71.449,
|
| 276 |
+
"step": 4400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.7,
|
| 280 |
+
"learning_rate": 2.1518987341772153e-05,
|
| 281 |
+
"loss": 0.0634,
|
| 282 |
+
"step": 4500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.82,
|
| 286 |
+
"eval_accuracy": 0.8110235929489136,
|
| 287 |
+
"eval_f1": 0.817490494296578,
|
| 288 |
+
"eval_loss": 0.6774270534515381,
|
| 289 |
+
"eval_runtime": 0.8879,
|
| 290 |
+
"eval_samples_per_second": 572.147,
|
| 291 |
+
"eval_steps_per_second": 72.081,
|
| 292 |
+
"step": 4600
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 6.08,
|
| 296 |
+
"eval_accuracy": 0.7992125749588013,
|
| 297 |
+
"eval_f1": 0.8038461538461538,
|
| 298 |
+
"eval_loss": 0.9549906849861145,
|
| 299 |
+
"eval_runtime": 0.9051,
|
| 300 |
+
"eval_samples_per_second": 561.292,
|
| 301 |
+
"eval_steps_per_second": 70.714,
|
| 302 |
+
"step": 4800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.33,
|
| 306 |
+
"learning_rate": 1.8354430379746836e-05,
|
| 307 |
+
"loss": 0.0548,
|
| 308 |
+
"step": 5000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.33,
|
| 312 |
+
"eval_accuracy": 0.8031495809555054,
|
| 313 |
+
"eval_f1": 0.8091603053435114,
|
| 314 |
+
"eval_loss": 1.1089578866958618,
|
| 315 |
+
"eval_runtime": 0.8777,
|
| 316 |
+
"eval_samples_per_second": 578.768,
|
| 317 |
+
"eval_steps_per_second": 72.916,
|
| 318 |
+
"step": 5000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 6.58,
|
| 322 |
+
"eval_accuracy": 0.8051180839538574,
|
| 323 |
+
"eval_f1": 0.809248554913295,
|
| 324 |
+
"eval_loss": 1.028864860534668,
|
| 325 |
+
"eval_runtime": 0.8922,
|
| 326 |
+
"eval_samples_per_second": 569.357,
|
| 327 |
+
"eval_steps_per_second": 71.73,
|
| 328 |
+
"step": 5200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 6.84,
|
| 332 |
+
"eval_accuracy": 0.7952755689620972,
|
| 333 |
+
"eval_f1": 0.8066914498141264,
|
| 334 |
+
"eval_loss": 0.9950660467147827,
|
| 335 |
+
"eval_runtime": 0.894,
|
| 336 |
+
"eval_samples_per_second": 568.236,
|
| 337 |
+
"eval_steps_per_second": 71.589,
|
| 338 |
+
"step": 5400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.96,
|
| 342 |
+
"learning_rate": 1.5189873417721521e-05,
|
| 343 |
+
"loss": 0.0473,
|
| 344 |
+
"step": 5500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 7.09,
|
| 348 |
+
"eval_accuracy": 0.8110235929489136,
|
| 349 |
+
"eval_f1": 0.8117647058823529,
|
| 350 |
+
"eval_loss": 1.1159313917160034,
|
| 351 |
+
"eval_runtime": 0.8468,
|
| 352 |
+
"eval_samples_per_second": 599.932,
|
| 353 |
+
"eval_steps_per_second": 75.582,
|
| 354 |
+
"step": 5600
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 7.34,
|
| 358 |
+
"eval_accuracy": 0.8090550899505615,
|
| 359 |
+
"eval_f1": 0.8131021194605009,
|
| 360 |
+
"eval_loss": 1.0203063488006592,
|
| 361 |
+
"eval_runtime": 0.9245,
|
| 362 |
+
"eval_samples_per_second": 549.472,
|
| 363 |
+
"eval_steps_per_second": 69.225,
|
| 364 |
+
"step": 5800
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 7.59,
|
| 368 |
+
"learning_rate": 1.2025316455696203e-05,
|
| 369 |
+
"loss": 0.036,
|
| 370 |
+
"step": 6000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 7.59,
|
| 374 |
+
"eval_accuracy": 0.8149606585502625,
|
| 375 |
+
"eval_f1": 0.815686274509804,
|
| 376 |
+
"eval_loss": 1.0656845569610596,
|
| 377 |
+
"eval_runtime": 0.9107,
|
| 378 |
+
"eval_samples_per_second": 557.814,
|
| 379 |
+
"eval_steps_per_second": 70.276,
|
| 380 |
+
"step": 6000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.85,
|
| 384 |
+
"eval_accuracy": 0.8129921555519104,
|
| 385 |
+
"eval_f1": 0.8140900195694716,
|
| 386 |
+
"eval_loss": 1.0237640142440796,
|
| 387 |
+
"eval_runtime": 0.85,
|
| 388 |
+
"eval_samples_per_second": 597.63,
|
| 389 |
+
"eval_steps_per_second": 75.292,
|
| 390 |
+
"step": 6200
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 8.1,
|
| 394 |
+
"eval_accuracy": 0.8208661675453186,
|
| 395 |
+
"eval_f1": 0.8205128205128205,
|
| 396 |
+
"eval_loss": 1.1597448587417603,
|
| 397 |
+
"eval_runtime": 0.8983,
|
| 398 |
+
"eval_samples_per_second": 565.501,
|
| 399 |
+
"eval_steps_per_second": 71.244,
|
| 400 |
+
"step": 6400
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 8.1,
|
| 404 |
+
"step": 6400,
|
| 405 |
+
"total_flos": 1.3556183708860416e+16,
|
| 406 |
+
"train_loss": 0.14836265951395033,
|
| 407 |
+
"train_runtime": 2029.2795,
|
| 408 |
+
"train_samples_per_second": 248.995,
|
| 409 |
+
"train_steps_per_second": 3.893
|
| 410 |
+
}
|
| 411 |
+
],
|
| 412 |
+
"max_steps": 7900,
|
| 413 |
+
"num_train_epochs": 10,
|
| 414 |
+
"total_flos": 1.3556183708860416e+16,
|
| 415 |
+
"trial_name": null,
|
| 416 |
+
"trial_params": null
|
| 417 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|