Instructions to use circlemachinelearning/bart-email-multitask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use circlemachinelearning/bart-email-multitask with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("circlemachinelearning/bart-email-multitask") model = AutoModelForSeq2SeqLM.from_pretrained("circlemachinelearning/bart-email-multitask", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 500, checkpoint
Browse files- last-checkpoint/config.json +68 -0
- last-checkpoint/generation_config.json +17 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +51 -0
- last-checkpoint/tokenizer_config.json +57 -0
- last-checkpoint/trainer_state.json +126 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_num_labels": 3,
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_final_layer_norm": false,
|
| 6 |
+
"architectures": [
|
| 7 |
+
"BartForConditionalGeneration"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"classif_dropout": 0.0,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 1024,
|
| 14 |
+
"decoder_attention_heads": 16,
|
| 15 |
+
"decoder_ffn_dim": 4096,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 12,
|
| 18 |
+
"decoder_start_token_id": 2,
|
| 19 |
+
"dropout": 0.1,
|
| 20 |
+
"dtype": "float32",
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"force_bos_token_to_be_generated": true,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"length_penalty": null,
|
| 43 |
+
"max_length": null,
|
| 44 |
+
"max_position_embeddings": 1024,
|
| 45 |
+
"min_length": null,
|
| 46 |
+
"model_type": "bart",
|
| 47 |
+
"no_repeat_ngram_size": null,
|
| 48 |
+
"normalize_before": false,
|
| 49 |
+
"num_beams": null,
|
| 50 |
+
"num_hidden_layers": 12,
|
| 51 |
+
"output_past": true,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"prefix": " ",
|
| 54 |
+
"scale_embedding": false,
|
| 55 |
+
"task_specific_params": {
|
| 56 |
+
"summarization": {
|
| 57 |
+
"early_stopping": true,
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"no_repeat_ngram_size": 3,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
+
"transformers_version": "4.57.5",
|
| 66 |
+
"use_cache": true,
|
| 67 |
+
"vocab_size": 50264
|
| 68 |
+
}
|
last-checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
2
|
| 7 |
+
],
|
| 8 |
+
"forced_bos_token_id": 0,
|
| 9 |
+
"forced_eos_token_id": 2,
|
| 10 |
+
"length_penalty": 2.0,
|
| 11 |
+
"max_length": 142,
|
| 12 |
+
"min_length": 56,
|
| 13 |
+
"no_repeat_ngram_size": 3,
|
| 14 |
+
"num_beams": 4,
|
| 15 |
+
"pad_token_id": 1,
|
| 16 |
+
"transformers_version": "4.57.5"
|
| 17 |
+
}
|
last-checkpoint/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8583659211c43c979e3ebb2b2077aaad30595ab37a9bef5343af02d10b4c8bfc
|
| 3 |
+
size 1625422896
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7bec18a84f551b816591479a6205f955cf887eb99a0dfe6f178ee390d2f2d15
|
| 3 |
+
size 3250759392
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c06cd809d24fd6588d7182ae83a04c71980b17187bed1fed3de7b640efbf43a
|
| 3 |
+
size 14645
|
last-checkpoint/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08a4ed0ac44c7cb5fe211aaac922c6c1f4955961ca56a185712498d587eefce0
|
| 3 |
+
size 1383
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6901005092102ab95f1173ef27f9dc91cdbf890535e1b1d5bd4fdb92b6125b7d
|
| 3 |
+
size 1465
|
last-checkpoint/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 |
+
}
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 500,
|
| 3 |
+
"best_metric": 49.45,
|
| 4 |
+
"best_model_checkpoint": "./bart-email-multitask-updated/checkpoint-500",
|
| 5 |
+
"epoch": 0.17260723224303098,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0172607232243031,
|
| 14 |
+
"grad_norm": 3.641310691833496,
|
| 15 |
+
"learning_rate": 1.2250000000000001e-06,
|
| 16 |
+
"loss": 0.4528,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0345214464486062,
|
| 21 |
+
"grad_norm": 2.5743606090545654,
|
| 22 |
+
"learning_rate": 2.475e-06,
|
| 23 |
+
"loss": 0.4354,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.051782169672909294,
|
| 28 |
+
"grad_norm": 2.6847357749938965,
|
| 29 |
+
"learning_rate": 3.7250000000000003e-06,
|
| 30 |
+
"loss": 0.4015,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0690428928972124,
|
| 35 |
+
"grad_norm": 2.5933823585510254,
|
| 36 |
+
"learning_rate": 4.975000000000001e-06,
|
| 37 |
+
"loss": 0.3952,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08630361612151549,
|
| 42 |
+
"grad_norm": 2.950077772140503,
|
| 43 |
+
"learning_rate": 4.956203074722918e-06,
|
| 44 |
+
"loss": 0.3744,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10356433934581859,
|
| 49 |
+
"grad_norm": 2.7843117713928223,
|
| 50 |
+
"learning_rate": 4.911512334644262e-06,
|
| 51 |
+
"loss": 0.3613,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12082506257012168,
|
| 56 |
+
"grad_norm": 2.70448637008667,
|
| 57 |
+
"learning_rate": 4.866821594565607e-06,
|
| 58 |
+
"loss": 0.321,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1380857857944248,
|
| 63 |
+
"grad_norm": 2.6096677780151367,
|
| 64 |
+
"learning_rate": 4.82213085448695e-06,
|
| 65 |
+
"loss": 0.3028,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.15534650901872787,
|
| 70 |
+
"grad_norm": 9.160786628723145,
|
| 71 |
+
"learning_rate": 4.777440114408295e-06,
|
| 72 |
+
"loss": 0.2841,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.17260723224303098,
|
| 77 |
+
"grad_norm": 3.1601881980895996,
|
| 78 |
+
"learning_rate": 4.732749374329639e-06,
|
| 79 |
+
"loss": 0.2866,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.17260723224303098,
|
| 84 |
+
"eval_gen_len": 56.13717277486911,
|
| 85 |
+
"eval_loss": 0.6366580128669739,
|
| 86 |
+
"eval_rouge1": 49.45,
|
| 87 |
+
"eval_rouge2": 34.98,
|
| 88 |
+
"eval_rougeL": 42.83,
|
| 89 |
+
"eval_rougeLsum": 43.35,
|
| 90 |
+
"eval_runtime": 3578.4556,
|
| 91 |
+
"eval_samples_per_second": 1.601,
|
| 92 |
+
"eval_steps_per_second": 0.4,
|
| 93 |
+
"step": 500
|
| 94 |
+
}
|
| 95 |
+
],
|
| 96 |
+
"logging_steps": 50,
|
| 97 |
+
"max_steps": 5794,
|
| 98 |
+
"num_input_tokens_seen": 0,
|
| 99 |
+
"num_train_epochs": 2,
|
| 100 |
+
"save_steps": 500,
|
| 101 |
+
"stateful_callbacks": {
|
| 102 |
+
"EarlyStoppingCallback": {
|
| 103 |
+
"args": {
|
| 104 |
+
"early_stopping_patience": 2,
|
| 105 |
+
"early_stopping_threshold": 0.0
|
| 106 |
+
},
|
| 107 |
+
"attributes": {
|
| 108 |
+
"early_stopping_patience_counter": 0
|
| 109 |
+
}
|
| 110 |
+
},
|
| 111 |
+
"TrainerControl": {
|
| 112 |
+
"args": {
|
| 113 |
+
"should_epoch_stop": false,
|
| 114 |
+
"should_evaluate": false,
|
| 115 |
+
"should_log": false,
|
| 116 |
+
"should_save": true,
|
| 117 |
+
"should_training_stop": false
|
| 118 |
+
},
|
| 119 |
+
"attributes": {}
|
| 120 |
+
}
|
| 121 |
+
},
|
| 122 |
+
"total_flos": 1.7167531769856e+16,
|
| 123 |
+
"train_batch_size": 4,
|
| 124 |
+
"trial_name": null,
|
| 125 |
+
"trial_params": null
|
| 126 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f20b49f2dc6c4d7679794c60ed6790a8246180ab315db49774772c1eaa1eee7
|
| 3 |
+
size 6033
|
last-checkpoint/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|