Upload folder using huggingface_hub
Browse files- checkpoint-54/config.json +73 -0
- checkpoint-54/generation_config.json +13 -0
- checkpoint-54/model.safetensors +3 -0
- checkpoint-54/optimizer.pt +3 -0
- checkpoint-54/rng_state.pth +3 -0
- checkpoint-54/scheduler.pt +3 -0
- checkpoint-54/trainer_state.json +435 -0
- checkpoint-54/training_args.bin +3 -0
- config.yml +39 -0
checkpoint-54/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 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 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"num_beams": null,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"scale_embedding": false,
|
| 49 |
+
"task_specific_params": {
|
| 50 |
+
"summarization": {
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 128,
|
| 53 |
+
"min_length": 12,
|
| 54 |
+
"num_beams": 4
|
| 55 |
+
},
|
| 56 |
+
"summarization_cnn": {
|
| 57 |
+
"length_penalty": 2.0,
|
| 58 |
+
"max_length": 142,
|
| 59 |
+
"min_length": 56,
|
| 60 |
+
"num_beams": 4
|
| 61 |
+
},
|
| 62 |
+
"summarization_xsum": {
|
| 63 |
+
"length_penalty": 1.0,
|
| 64 |
+
"max_length": 62,
|
| 65 |
+
"min_length": 11,
|
| 66 |
+
"num_beams": 6
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
"torch_dtype": "float32",
|
| 70 |
+
"transformers_version": "4.49.0",
|
| 71 |
+
"use_cache": true,
|
| 72 |
+
"vocab_size": 50265
|
| 73 |
+
}
|
checkpoint-54/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.49.0"
|
| 13 |
+
}
|
checkpoint-54/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e37a421b2230ce4663ff5fe7c72c4a265d2f5cea502ef1243f3f27fd89f24eaa
|
| 3 |
+
size 1625426996
|
checkpoint-54/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b4a8876fafdb6b87a55d3079a2bf162c9c4fff11bfbb9f6c22a787ce566ae1e
|
| 3 |
+
size 3250759951
|
checkpoint-54/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b37cf41a65d414c84d053457ea0c5a74ed14f5a0990336aecb278a790818b59
|
| 3 |
+
size 14244
|
checkpoint-54/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a59d0db56ae0657b548bad63e4c01c91ef98082dd18463ca96dbc6eb3496b4b7
|
| 3 |
+
size 1064
|
checkpoint-54/trainer_state.json
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 8.006572723388672,
|
| 3 |
+
"best_model_checkpoint": "/workspaces/wakin_bake/trained_seq2seq/checkpoint-54",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 54,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05555555555555555,
|
| 13 |
+
"grad_norm": 232.05528259277344,
|
| 14 |
+
"learning_rate": 2.9444444444444445e-05,
|
| 15 |
+
"loss": 15.5552,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1111111111111111,
|
| 20 |
+
"grad_norm": 625.3634643554688,
|
| 21 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 22 |
+
"loss": 13.7158,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16666666666666666,
|
| 27 |
+
"grad_norm": 241.36074829101562,
|
| 28 |
+
"learning_rate": 2.8333333333333332e-05,
|
| 29 |
+
"loss": 14.5239,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2222222222222222,
|
| 34 |
+
"grad_norm": 144.937744140625,
|
| 35 |
+
"learning_rate": 2.777777777777778e-05,
|
| 36 |
+
"loss": 11.9337,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2777777777777778,
|
| 41 |
+
"grad_norm": 59.95172119140625,
|
| 42 |
+
"learning_rate": 2.7222222222222223e-05,
|
| 43 |
+
"loss": 12.6623,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3333333333333333,
|
| 48 |
+
"grad_norm": 70.46778869628906,
|
| 49 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 50 |
+
"loss": 13.4721,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3888888888888889,
|
| 55 |
+
"grad_norm": 26.51784324645996,
|
| 56 |
+
"learning_rate": 2.611111111111111e-05,
|
| 57 |
+
"loss": 11.7672,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4444444444444444,
|
| 62 |
+
"grad_norm": 34.07495880126953,
|
| 63 |
+
"learning_rate": 2.5555555555555557e-05,
|
| 64 |
+
"loss": 10.9863,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5,
|
| 69 |
+
"grad_norm": 17.962387084960938,
|
| 70 |
+
"learning_rate": 2.5e-05,
|
| 71 |
+
"loss": 11.6291,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5555555555555556,
|
| 76 |
+
"grad_norm": 14.597478866577148,
|
| 77 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 78 |
+
"loss": 11.5824,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6111111111111112,
|
| 83 |
+
"grad_norm": 18.746841430664062,
|
| 84 |
+
"learning_rate": 2.388888888888889e-05,
|
| 85 |
+
"loss": 12.5436,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6666666666666666,
|
| 90 |
+
"grad_norm": 16.38216209411621,
|
| 91 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 92 |
+
"loss": 10.9329,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7222222222222222,
|
| 97 |
+
"grad_norm": 12.897452354431152,
|
| 98 |
+
"learning_rate": 2.277777777777778e-05,
|
| 99 |
+
"loss": 10.3338,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7777777777777778,
|
| 104 |
+
"grad_norm": 16.33725357055664,
|
| 105 |
+
"learning_rate": 2.222222222222222e-05,
|
| 106 |
+
"loss": 12.2682,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8333333333333334,
|
| 111 |
+
"grad_norm": 16.713655471801758,
|
| 112 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 113 |
+
"loss": 11.125,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8888888888888888,
|
| 118 |
+
"grad_norm": 12.658448219299316,
|
| 119 |
+
"learning_rate": 2.111111111111111e-05,
|
| 120 |
+
"loss": 10.3801,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9444444444444444,
|
| 125 |
+
"grad_norm": 18.49787712097168,
|
| 126 |
+
"learning_rate": 2.0555555555555558e-05,
|
| 127 |
+
"loss": 11.9023,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"grad_norm": 11.225893020629883,
|
| 133 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 134 |
+
"loss": 10.0598,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_loss": 8.97833251953125,
|
| 140 |
+
"eval_runtime": 17.0971,
|
| 141 |
+
"eval_samples_per_second": 0.468,
|
| 142 |
+
"eval_steps_per_second": 0.117,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.0555555555555556,
|
| 147 |
+
"grad_norm": 17.131927490234375,
|
| 148 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 149 |
+
"loss": 11.6307,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.1111111111111112,
|
| 154 |
+
"grad_norm": 11.501855850219727,
|
| 155 |
+
"learning_rate": 1.888888888888889e-05,
|
| 156 |
+
"loss": 9.9624,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.1666666666666667,
|
| 161 |
+
"grad_norm": 18.79712677001953,
|
| 162 |
+
"learning_rate": 1.8333333333333336e-05,
|
| 163 |
+
"loss": 11.3912,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.2222222222222223,
|
| 168 |
+
"grad_norm": 14.980157852172852,
|
| 169 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 170 |
+
"loss": 9.997,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.2777777777777777,
|
| 175 |
+
"grad_norm": 17.382972717285156,
|
| 176 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 177 |
+
"loss": 9.7999,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.3333333333333333,
|
| 182 |
+
"grad_norm": 14.6889009475708,
|
| 183 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 184 |
+
"loss": 9.5019,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.3888888888888888,
|
| 189 |
+
"grad_norm": 11.028532028198242,
|
| 190 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 191 |
+
"loss": 8.4348,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.4444444444444444,
|
| 196 |
+
"grad_norm": 19.165592193603516,
|
| 197 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 198 |
+
"loss": 10.2169,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.5,
|
| 203 |
+
"grad_norm": 11.539628028869629,
|
| 204 |
+
"learning_rate": 1.5e-05,
|
| 205 |
+
"loss": 8.5594,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.5555555555555556,
|
| 210 |
+
"grad_norm": 20.748764038085938,
|
| 211 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 212 |
+
"loss": 9.8663,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.6111111111111112,
|
| 217 |
+
"grad_norm": 25.90353012084961,
|
| 218 |
+
"learning_rate": 1.388888888888889e-05,
|
| 219 |
+
"loss": 10.4679,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.6666666666666665,
|
| 224 |
+
"grad_norm": 12.756267547607422,
|
| 225 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 226 |
+
"loss": 8.8323,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.7222222222222223,
|
| 231 |
+
"grad_norm": 27.25147247314453,
|
| 232 |
+
"learning_rate": 1.2777777777777779e-05,
|
| 233 |
+
"loss": 10.2936,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.7777777777777777,
|
| 238 |
+
"grad_norm": 14.550564765930176,
|
| 239 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 240 |
+
"loss": 8.4467,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.8333333333333335,
|
| 245 |
+
"grad_norm": 15.393588066101074,
|
| 246 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 247 |
+
"loss": 8.4903,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.8888888888888888,
|
| 252 |
+
"grad_norm": 22.393354415893555,
|
| 253 |
+
"learning_rate": 1.111111111111111e-05,
|
| 254 |
+
"loss": 8.7652,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.9444444444444444,
|
| 259 |
+
"grad_norm": 24.291881561279297,
|
| 260 |
+
"learning_rate": 1.0555555555555555e-05,
|
| 261 |
+
"loss": 9.3748,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.0,
|
| 266 |
+
"grad_norm": 30.40011215209961,
|
| 267 |
+
"learning_rate": 9.999999999999999e-06,
|
| 268 |
+
"loss": 9.7655,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.0,
|
| 273 |
+
"eval_loss": 8.464545249938965,
|
| 274 |
+
"eval_runtime": 13.5018,
|
| 275 |
+
"eval_samples_per_second": 0.593,
|
| 276 |
+
"eval_steps_per_second": 0.148,
|
| 277 |
+
"step": 36
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.0555555555555554,
|
| 281 |
+
"grad_norm": 23.087289810180664,
|
| 282 |
+
"learning_rate": 9.444444444444445e-06,
|
| 283 |
+
"loss": 8.9217,
|
| 284 |
+
"step": 37
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.111111111111111,
|
| 288 |
+
"grad_norm": 26.975997924804688,
|
| 289 |
+
"learning_rate": 8.888888888888888e-06,
|
| 290 |
+
"loss": 8.8655,
|
| 291 |
+
"step": 38
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.1666666666666665,
|
| 295 |
+
"grad_norm": 28.121719360351562,
|
| 296 |
+
"learning_rate": 8.333333333333334e-06,
|
| 297 |
+
"loss": 9.1362,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.2222222222222223,
|
| 302 |
+
"grad_norm": 28.4269962310791,
|
| 303 |
+
"learning_rate": 7.777777777777777e-06,
|
| 304 |
+
"loss": 9.2849,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.2777777777777777,
|
| 309 |
+
"grad_norm": 31.212228775024414,
|
| 310 |
+
"learning_rate": 7.222222222222222e-06,
|
| 311 |
+
"loss": 9.5769,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.3333333333333335,
|
| 316 |
+
"grad_norm": 27.985774993896484,
|
| 317 |
+
"learning_rate": 6.666666666666667e-06,
|
| 318 |
+
"loss": 8.6151,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.388888888888889,
|
| 323 |
+
"grad_norm": 29.317476272583008,
|
| 324 |
+
"learning_rate": 6.111111111111111e-06,
|
| 325 |
+
"loss": 8.8767,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.4444444444444446,
|
| 330 |
+
"grad_norm": 16.052814483642578,
|
| 331 |
+
"learning_rate": 5.555555555555555e-06,
|
| 332 |
+
"loss": 7.3641,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.5,
|
| 337 |
+
"grad_norm": 22.66093635559082,
|
| 338 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 339 |
+
"loss": 7.9935,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.5555555555555554,
|
| 344 |
+
"grad_norm": 39.148033142089844,
|
| 345 |
+
"learning_rate": 4.444444444444444e-06,
|
| 346 |
+
"loss": 8.8332,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.611111111111111,
|
| 351 |
+
"grad_norm": 39.017677307128906,
|
| 352 |
+
"learning_rate": 3.888888888888889e-06,
|
| 353 |
+
"loss": 8.779,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.6666666666666665,
|
| 358 |
+
"grad_norm": 26.151742935180664,
|
| 359 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 360 |
+
"loss": 7.5859,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.7222222222222223,
|
| 365 |
+
"grad_norm": 32.05317306518555,
|
| 366 |
+
"learning_rate": 2.7777777777777775e-06,
|
| 367 |
+
"loss": 8.2961,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.7777777777777777,
|
| 372 |
+
"grad_norm": 31.795818328857422,
|
| 373 |
+
"learning_rate": 2.222222222222222e-06,
|
| 374 |
+
"loss": 8.156,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.8333333333333335,
|
| 379 |
+
"grad_norm": 22.7334041595459,
|
| 380 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 381 |
+
"loss": 7.9457,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.888888888888889,
|
| 386 |
+
"grad_norm": 16.970556259155273,
|
| 387 |
+
"learning_rate": 1.111111111111111e-06,
|
| 388 |
+
"loss": 7.734,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.9444444444444446,
|
| 393 |
+
"grad_norm": 31.753923416137695,
|
| 394 |
+
"learning_rate": 5.555555555555555e-07,
|
| 395 |
+
"loss": 7.925,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.0,
|
| 400 |
+
"grad_norm": 22.566757202148438,
|
| 401 |
+
"learning_rate": 0.0,
|
| 402 |
+
"loss": 7.174,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.0,
|
| 407 |
+
"eval_loss": 8.006572723388672,
|
| 408 |
+
"eval_runtime": 32.8904,
|
| 409 |
+
"eval_samples_per_second": 0.243,
|
| 410 |
+
"eval_steps_per_second": 0.061,
|
| 411 |
+
"step": 54
|
| 412 |
+
}
|
| 413 |
+
],
|
| 414 |
+
"logging_steps": 1,
|
| 415 |
+
"max_steps": 54,
|
| 416 |
+
"num_input_tokens_seen": 0,
|
| 417 |
+
"num_train_epochs": 3,
|
| 418 |
+
"save_steps": 350,
|
| 419 |
+
"stateful_callbacks": {
|
| 420 |
+
"TrainerControl": {
|
| 421 |
+
"args": {
|
| 422 |
+
"should_epoch_stop": false,
|
| 423 |
+
"should_evaluate": false,
|
| 424 |
+
"should_log": false,
|
| 425 |
+
"should_save": true,
|
| 426 |
+
"should_training_stop": true
|
| 427 |
+
},
|
| 428 |
+
"attributes": {}
|
| 429 |
+
}
|
| 430 |
+
},
|
| 431 |
+
"total_flos": 234047297028096.0,
|
| 432 |
+
"train_batch_size": 4,
|
| 433 |
+
"trial_name": null,
|
| 434 |
+
"trial_params": null
|
| 435 |
+
}
|
checkpoint-54/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e593890fe75ce69803129a0e830969214a03cc319705ba065cb2f3248fce091
|
| 3 |
+
size 5368
|
config.yml
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
datasets:
|
| 2 |
+
- name: Scottie201/seq2seq_data
|
| 3 |
+
split: train
|
| 4 |
+
- name: Scottie201/seq2seq_data
|
| 5 |
+
split: validation
|
| 6 |
+
decision:
|
| 7 |
+
continue_training: false
|
| 8 |
+
reason: Model performance has not improved enough to warrant continued training.
|
| 9 |
+
suggestions:
|
| 10 |
+
- Consider adjusting the learning rate.
|
| 11 |
+
- Review training data for any inconsistencies.
|
| 12 |
+
model:
|
| 13 |
+
architecture: seq2seq
|
| 14 |
+
base_model: facebook/bart-large
|
| 15 |
+
batch_size: 4
|
| 16 |
+
epochs: 3
|
| 17 |
+
learning_rate: 3e-5
|
| 18 |
+
output_dir: /workspaces/wakin_bake/trained_seq2seq
|
| 19 |
+
resources:
|
| 20 |
+
device_map: auto
|
| 21 |
+
torch_dtype: bfloat16
|
| 22 |
+
use_gpu: true
|
| 23 |
+
tokenization:
|
| 24 |
+
max_length: 512
|
| 25 |
+
padding: max_length
|
| 26 |
+
source_column: input_text
|
| 27 |
+
target_column: target_text
|
| 28 |
+
truncation: true
|
| 29 |
+
training_args:
|
| 30 |
+
eval_strategy: epoch
|
| 31 |
+
generation_max_length: 150
|
| 32 |
+
generation_num_beams: 5
|
| 33 |
+
hub_model_id: Scottie201/seq2seq_finetuned
|
| 34 |
+
logging_dir: ./logs
|
| 35 |
+
logging_steps: 1
|
| 36 |
+
push_to_hub: true
|
| 37 |
+
save_steps: 350
|
| 38 |
+
save_total_limit: 1
|
| 39 |
+
training_continue: false
|