Upload with huggingface_hub
Browse files- checkpoint-21000/config.json +33 -0
- checkpoint-21000/optimizer.pt +3 -0
- checkpoint-21000/pytorch_model.bin +3 -0
- checkpoint-21000/rng_state.pth +3 -0
- checkpoint-21000/scheduler.pt +3 -0
- checkpoint-21000/trainer_state.json +818 -0
- checkpoint-21000/training_args.bin +3 -0
- config.json +33 -0
- lipo.out +472 -0
- pytorch_model.bin +3 -0
- runs/Apr09_13-58-13_lotan/1649512701.6283627/events.out.tfevents.1649512701.lotan.2908185.1 +3 -0
- runs/Apr09_13-58-13_lotan/events.out.tfevents.1649512701.lotan.2908185.0 +3 -0
- training_args.bin +3 -0
checkpoint-21000/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/saved_models/our_90epochs_saved_model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSelfiesClassification"
|
| 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": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 514,
|
| 23 |
+
"model_type": "roberta",
|
| 24 |
+
"num_attention_heads": 4,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 1,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.15.0",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 800
|
| 33 |
+
}
|
checkpoint-21000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ae424f57818b8c7281b11882188d0bc5b57e056c5f77a07be5c101a115f148f
|
| 3 |
+
size 693374749
|
checkpoint-21000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3b51560e9cff09ca9b47178b881764ff5e594c97346769443ee5b9568d55d1
|
| 3 |
+
size 349077673
|
checkpoint-21000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b2a022f7e044d07696f94718f90207ade05dfbd66408a5e53a1eb8afe63aa79
|
| 3 |
+
size 14503
|
checkpoint-21000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:120008236cc2182e850937aa9c39923b63980976fbcf0f01f26642c3d43b0810
|
| 3 |
+
size 623
|
checkpoint-21000/trainer_state.json
ADDED
|
@@ -0,0 +1,818 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 21000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_loss": 0.7975520491600037,
|
| 13 |
+
"eval_mae": 0.7266795039176941,
|
| 14 |
+
"eval_mse": 0.7975521087646484,
|
| 15 |
+
"eval_rmse": 0.8930577039718628,
|
| 16 |
+
"eval_runtime": 2.2756,
|
| 17 |
+
"eval_samples_per_second": 184.568,
|
| 18 |
+
"eval_steps_per_second": 23.291,
|
| 19 |
+
"step": 420
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 1.19,
|
| 23 |
+
"learning_rate": 9.761904761904762e-06,
|
| 24 |
+
"loss": 1.111,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"eval_loss": 0.609792947769165,
|
| 30 |
+
"eval_mae": 0.6158387660980225,
|
| 31 |
+
"eval_mse": 0.609792947769165,
|
| 32 |
+
"eval_rmse": 0.7808924317359924,
|
| 33 |
+
"eval_runtime": 1.9303,
|
| 34 |
+
"eval_samples_per_second": 217.582,
|
| 35 |
+
"eval_steps_per_second": 27.457,
|
| 36 |
+
"step": 840
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.38,
|
| 40 |
+
"learning_rate": 9.523809523809525e-06,
|
| 41 |
+
"loss": 0.4808,
|
| 42 |
+
"step": 1000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 0.6106507182121277,
|
| 47 |
+
"eval_mae": 0.5975062847137451,
|
| 48 |
+
"eval_mse": 0.6106507778167725,
|
| 49 |
+
"eval_rmse": 0.7814414501190186,
|
| 50 |
+
"eval_runtime": 2.7602,
|
| 51 |
+
"eval_samples_per_second": 152.163,
|
| 52 |
+
"eval_steps_per_second": 19.202,
|
| 53 |
+
"step": 1260
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.57,
|
| 57 |
+
"learning_rate": 9.285714285714288e-06,
|
| 58 |
+
"loss": 0.3196,
|
| 59 |
+
"step": 1500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_loss": 0.5748845338821411,
|
| 64 |
+
"eval_mae": 0.584411084651947,
|
| 65 |
+
"eval_mse": 0.5748845934867859,
|
| 66 |
+
"eval_rmse": 0.7582114338874817,
|
| 67 |
+
"eval_runtime": 1.9617,
|
| 68 |
+
"eval_samples_per_second": 214.099,
|
| 69 |
+
"eval_steps_per_second": 27.017,
|
| 70 |
+
"step": 1680
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 4.76,
|
| 74 |
+
"learning_rate": 9.047619047619049e-06,
|
| 75 |
+
"loss": 0.2357,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.0,
|
| 80 |
+
"eval_loss": 0.6165366172790527,
|
| 81 |
+
"eval_mae": 0.5906195640563965,
|
| 82 |
+
"eval_mse": 0.6165366172790527,
|
| 83 |
+
"eval_rmse": 0.785198450088501,
|
| 84 |
+
"eval_runtime": 2.7689,
|
| 85 |
+
"eval_samples_per_second": 151.687,
|
| 86 |
+
"eval_steps_per_second": 19.141,
|
| 87 |
+
"step": 2100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 5.95,
|
| 91 |
+
"learning_rate": 8.80952380952381e-06,
|
| 92 |
+
"loss": 0.1909,
|
| 93 |
+
"step": 2500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.0,
|
| 97 |
+
"eval_loss": 0.5579051375389099,
|
| 98 |
+
"eval_mae": 0.5814845561981201,
|
| 99 |
+
"eval_mse": 0.5579050779342651,
|
| 100 |
+
"eval_rmse": 0.7469304203987122,
|
| 101 |
+
"eval_runtime": 1.2975,
|
| 102 |
+
"eval_samples_per_second": 323.7,
|
| 103 |
+
"eval_steps_per_second": 40.848,
|
| 104 |
+
"step": 2520
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"eval_loss": 0.5374110341072083,
|
| 109 |
+
"eval_mae": 0.5643972754478455,
|
| 110 |
+
"eval_mse": 0.5374110341072083,
|
| 111 |
+
"eval_rmse": 0.7330832481384277,
|
| 112 |
+
"eval_runtime": 2.8385,
|
| 113 |
+
"eval_samples_per_second": 147.967,
|
| 114 |
+
"eval_steps_per_second": 18.672,
|
| 115 |
+
"step": 2940
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 7.14,
|
| 119 |
+
"learning_rate": 8.571428571428571e-06,
|
| 120 |
+
"loss": 0.157,
|
| 121 |
+
"step": 3000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_loss": 0.5414829850196838,
|
| 126 |
+
"eval_mae": 0.5653696060180664,
|
| 127 |
+
"eval_mse": 0.5414829254150391,
|
| 128 |
+
"eval_rmse": 0.735855221748352,
|
| 129 |
+
"eval_runtime": 2.0614,
|
| 130 |
+
"eval_samples_per_second": 203.747,
|
| 131 |
+
"eval_steps_per_second": 25.711,
|
| 132 |
+
"step": 3360
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 8.33,
|
| 136 |
+
"learning_rate": 8.333333333333334e-06,
|
| 137 |
+
"loss": 0.1334,
|
| 138 |
+
"step": 3500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 9.0,
|
| 142 |
+
"eval_loss": 0.5609115958213806,
|
| 143 |
+
"eval_mae": 0.5715270042419434,
|
| 144 |
+
"eval_mse": 0.5609115362167358,
|
| 145 |
+
"eval_rmse": 0.7489402890205383,
|
| 146 |
+
"eval_runtime": 1.9712,
|
| 147 |
+
"eval_samples_per_second": 213.066,
|
| 148 |
+
"eval_steps_per_second": 26.887,
|
| 149 |
+
"step": 3780
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 9.52,
|
| 153 |
+
"learning_rate": 8.095238095238097e-06,
|
| 154 |
+
"loss": 0.1199,
|
| 155 |
+
"step": 4000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.0,
|
| 159 |
+
"eval_loss": 0.5141286253929138,
|
| 160 |
+
"eval_mae": 0.5450649261474609,
|
| 161 |
+
"eval_mse": 0.5141286253929138,
|
| 162 |
+
"eval_rmse": 0.7170276045799255,
|
| 163 |
+
"eval_runtime": 1.9528,
|
| 164 |
+
"eval_samples_per_second": 215.081,
|
| 165 |
+
"eval_steps_per_second": 27.141,
|
| 166 |
+
"step": 4200
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 10.71,
|
| 170 |
+
"learning_rate": 7.857142857142858e-06,
|
| 171 |
+
"loss": 0.1112,
|
| 172 |
+
"step": 4500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 11.0,
|
| 176 |
+
"eval_loss": 0.5070027112960815,
|
| 177 |
+
"eval_mae": 0.5421043634414673,
|
| 178 |
+
"eval_mse": 0.5070027112960815,
|
| 179 |
+
"eval_rmse": 0.7120411992073059,
|
| 180 |
+
"eval_runtime": 1.3515,
|
| 181 |
+
"eval_samples_per_second": 310.772,
|
| 182 |
+
"eval_steps_per_second": 39.216,
|
| 183 |
+
"step": 4620
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 11.9,
|
| 187 |
+
"learning_rate": 7.61904761904762e-06,
|
| 188 |
+
"loss": 0.0983,
|
| 189 |
+
"step": 5000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 12.0,
|
| 193 |
+
"eval_loss": 0.5180405378341675,
|
| 194 |
+
"eval_mae": 0.5500118732452393,
|
| 195 |
+
"eval_mse": 0.5180405378341675,
|
| 196 |
+
"eval_rmse": 0.7197503447532654,
|
| 197 |
+
"eval_runtime": 1.2448,
|
| 198 |
+
"eval_samples_per_second": 337.399,
|
| 199 |
+
"eval_steps_per_second": 42.577,
|
| 200 |
+
"step": 5040
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"eval_loss": 0.5257736444473267,
|
| 205 |
+
"eval_mae": 0.561431348323822,
|
| 206 |
+
"eval_mse": 0.5257736444473267,
|
| 207 |
+
"eval_rmse": 0.7251024842262268,
|
| 208 |
+
"eval_runtime": 1.1775,
|
| 209 |
+
"eval_samples_per_second": 356.675,
|
| 210 |
+
"eval_steps_per_second": 45.009,
|
| 211 |
+
"step": 5460
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 13.1,
|
| 215 |
+
"learning_rate": 7.380952380952382e-06,
|
| 216 |
+
"loss": 0.0861,
|
| 217 |
+
"step": 5500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"eval_loss": 0.5195261836051941,
|
| 222 |
+
"eval_mae": 0.5508889555931091,
|
| 223 |
+
"eval_mse": 0.5195261836051941,
|
| 224 |
+
"eval_rmse": 0.7207816243171692,
|
| 225 |
+
"eval_runtime": 1.2061,
|
| 226 |
+
"eval_samples_per_second": 348.216,
|
| 227 |
+
"eval_steps_per_second": 43.942,
|
| 228 |
+
"step": 5880
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 14.29,
|
| 232 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 233 |
+
"loss": 0.0833,
|
| 234 |
+
"step": 6000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 15.0,
|
| 238 |
+
"eval_loss": 0.5224341154098511,
|
| 239 |
+
"eval_mae": 0.552178144454956,
|
| 240 |
+
"eval_mse": 0.5224341154098511,
|
| 241 |
+
"eval_rmse": 0.7227960228919983,
|
| 242 |
+
"eval_runtime": 1.1671,
|
| 243 |
+
"eval_samples_per_second": 359.858,
|
| 244 |
+
"eval_steps_per_second": 45.411,
|
| 245 |
+
"step": 6300
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 15.48,
|
| 249 |
+
"learning_rate": 6.9047619047619055e-06,
|
| 250 |
+
"loss": 0.0741,
|
| 251 |
+
"step": 6500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 16.0,
|
| 255 |
+
"eval_loss": 0.5121651291847229,
|
| 256 |
+
"eval_mae": 0.5470804572105408,
|
| 257 |
+
"eval_mse": 0.5121651291847229,
|
| 258 |
+
"eval_rmse": 0.715657114982605,
|
| 259 |
+
"eval_runtime": 1.1174,
|
| 260 |
+
"eval_samples_per_second": 375.865,
|
| 261 |
+
"eval_steps_per_second": 47.431,
|
| 262 |
+
"step": 6720
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 16.67,
|
| 266 |
+
"learning_rate": 6.666666666666667e-06,
|
| 267 |
+
"loss": 0.0744,
|
| 268 |
+
"step": 7000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 17.0,
|
| 272 |
+
"eval_loss": 0.4920870065689087,
|
| 273 |
+
"eval_mae": 0.5328148007392883,
|
| 274 |
+
"eval_mse": 0.4920870065689087,
|
| 275 |
+
"eval_rmse": 0.7014891505241394,
|
| 276 |
+
"eval_runtime": 1.1494,
|
| 277 |
+
"eval_samples_per_second": 365.42,
|
| 278 |
+
"eval_steps_per_second": 46.112,
|
| 279 |
+
"step": 7140
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 17.86,
|
| 283 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 284 |
+
"loss": 0.0649,
|
| 285 |
+
"step": 7500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 18.0,
|
| 289 |
+
"eval_loss": 0.5028687119483948,
|
| 290 |
+
"eval_mae": 0.5357252359390259,
|
| 291 |
+
"eval_mse": 0.5028687119483948,
|
| 292 |
+
"eval_rmse": 0.7091323733329773,
|
| 293 |
+
"eval_runtime": 1.3327,
|
| 294 |
+
"eval_samples_per_second": 315.156,
|
| 295 |
+
"eval_steps_per_second": 39.77,
|
| 296 |
+
"step": 7560
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 19.0,
|
| 300 |
+
"eval_loss": 0.526236891746521,
|
| 301 |
+
"eval_mae": 0.5603699684143066,
|
| 302 |
+
"eval_mse": 0.526236891746521,
|
| 303 |
+
"eval_rmse": 0.7254218459129333,
|
| 304 |
+
"eval_runtime": 1.2696,
|
| 305 |
+
"eval_samples_per_second": 330.822,
|
| 306 |
+
"eval_steps_per_second": 41.747,
|
| 307 |
+
"step": 7980
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 19.05,
|
| 311 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 312 |
+
"loss": 0.0639,
|
| 313 |
+
"step": 8000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"eval_loss": 0.5124732851982117,
|
| 318 |
+
"eval_mae": 0.5440532565116882,
|
| 319 |
+
"eval_mse": 0.5124732851982117,
|
| 320 |
+
"eval_rmse": 0.7158724069595337,
|
| 321 |
+
"eval_runtime": 1.139,
|
| 322 |
+
"eval_samples_per_second": 368.742,
|
| 323 |
+
"eval_steps_per_second": 46.532,
|
| 324 |
+
"step": 8400
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 20.24,
|
| 328 |
+
"learning_rate": 5.9523809523809525e-06,
|
| 329 |
+
"loss": 0.0609,
|
| 330 |
+
"step": 8500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 21.0,
|
| 334 |
+
"eval_loss": 0.4891616106033325,
|
| 335 |
+
"eval_mae": 0.5339100956916809,
|
| 336 |
+
"eval_mse": 0.48916158080101013,
|
| 337 |
+
"eval_rmse": 0.6994009017944336,
|
| 338 |
+
"eval_runtime": 1.0834,
|
| 339 |
+
"eval_samples_per_second": 387.673,
|
| 340 |
+
"eval_steps_per_second": 48.921,
|
| 341 |
+
"step": 8820
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 21.43,
|
| 345 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 346 |
+
"loss": 0.0547,
|
| 347 |
+
"step": 9000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 22.0,
|
| 351 |
+
"eval_loss": 0.4973764717578888,
|
| 352 |
+
"eval_mae": 0.5337387919425964,
|
| 353 |
+
"eval_mse": 0.4973764419555664,
|
| 354 |
+
"eval_rmse": 0.7052491903305054,
|
| 355 |
+
"eval_runtime": 1.1768,
|
| 356 |
+
"eval_samples_per_second": 356.886,
|
| 357 |
+
"eval_steps_per_second": 45.036,
|
| 358 |
+
"step": 9240
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 22.62,
|
| 362 |
+
"learning_rate": 5.476190476190477e-06,
|
| 363 |
+
"loss": 0.0528,
|
| 364 |
+
"step": 9500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 23.0,
|
| 368 |
+
"eval_loss": 0.4779137670993805,
|
| 369 |
+
"eval_mae": 0.5240978598594666,
|
| 370 |
+
"eval_mse": 0.47791385650634766,
|
| 371 |
+
"eval_rmse": 0.6913131475448608,
|
| 372 |
+
"eval_runtime": 1.1884,
|
| 373 |
+
"eval_samples_per_second": 353.429,
|
| 374 |
+
"eval_steps_per_second": 44.599,
|
| 375 |
+
"step": 9660
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 23.81,
|
| 379 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 380 |
+
"loss": 0.0514,
|
| 381 |
+
"step": 10000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 24.0,
|
| 385 |
+
"eval_loss": 0.483572781085968,
|
| 386 |
+
"eval_mae": 0.5290801525115967,
|
| 387 |
+
"eval_mse": 0.48357275128364563,
|
| 388 |
+
"eval_rmse": 0.695393979549408,
|
| 389 |
+
"eval_runtime": 1.1926,
|
| 390 |
+
"eval_samples_per_second": 352.184,
|
| 391 |
+
"eval_steps_per_second": 44.442,
|
| 392 |
+
"step": 10080
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 25.0,
|
| 396 |
+
"learning_rate": 5e-06,
|
| 397 |
+
"loss": 0.0516,
|
| 398 |
+
"step": 10500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 25.0,
|
| 402 |
+
"eval_loss": 0.4979321360588074,
|
| 403 |
+
"eval_mae": 0.5313663482666016,
|
| 404 |
+
"eval_mse": 0.49793222546577454,
|
| 405 |
+
"eval_rmse": 0.7056431174278259,
|
| 406 |
+
"eval_runtime": 1.1676,
|
| 407 |
+
"eval_samples_per_second": 359.71,
|
| 408 |
+
"eval_steps_per_second": 45.392,
|
| 409 |
+
"step": 10500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 26.0,
|
| 413 |
+
"eval_loss": 0.48045653104782104,
|
| 414 |
+
"eval_mae": 0.530644416809082,
|
| 415 |
+
"eval_mse": 0.48045653104782104,
|
| 416 |
+
"eval_rmse": 0.693149745464325,
|
| 417 |
+
"eval_runtime": 1.1924,
|
| 418 |
+
"eval_samples_per_second": 352.222,
|
| 419 |
+
"eval_steps_per_second": 44.447,
|
| 420 |
+
"step": 10920
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 26.19,
|
| 424 |
+
"learning_rate": 4.761904761904762e-06,
|
| 425 |
+
"loss": 0.0463,
|
| 426 |
+
"step": 11000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 27.0,
|
| 430 |
+
"eval_loss": 0.48534154891967773,
|
| 431 |
+
"eval_mae": 0.5263835191726685,
|
| 432 |
+
"eval_mse": 0.48534154891967773,
|
| 433 |
+
"eval_rmse": 0.696664571762085,
|
| 434 |
+
"eval_runtime": 1.1385,
|
| 435 |
+
"eval_samples_per_second": 368.9,
|
| 436 |
+
"eval_steps_per_second": 46.552,
|
| 437 |
+
"step": 11340
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 27.38,
|
| 441 |
+
"learning_rate": 4.523809523809524e-06,
|
| 442 |
+
"loss": 0.0451,
|
| 443 |
+
"step": 11500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 28.0,
|
| 447 |
+
"eval_loss": 0.4952319264411926,
|
| 448 |
+
"eval_mae": 0.5382465720176697,
|
| 449 |
+
"eval_mse": 0.4952319264411926,
|
| 450 |
+
"eval_rmse": 0.7037271857261658,
|
| 451 |
+
"eval_runtime": 1.1142,
|
| 452 |
+
"eval_samples_per_second": 376.951,
|
| 453 |
+
"eval_steps_per_second": 47.568,
|
| 454 |
+
"step": 11760
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 28.57,
|
| 458 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 459 |
+
"loss": 0.0428,
|
| 460 |
+
"step": 12000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 29.0,
|
| 464 |
+
"eval_loss": 0.48455557227134705,
|
| 465 |
+
"eval_mae": 0.529035210609436,
|
| 466 |
+
"eval_mse": 0.48455557227134705,
|
| 467 |
+
"eval_rmse": 0.6961002349853516,
|
| 468 |
+
"eval_runtime": 1.1847,
|
| 469 |
+
"eval_samples_per_second": 354.512,
|
| 470 |
+
"eval_steps_per_second": 44.736,
|
| 471 |
+
"step": 12180
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 29.76,
|
| 475 |
+
"learning_rate": 4.047619047619048e-06,
|
| 476 |
+
"loss": 0.0417,
|
| 477 |
+
"step": 12500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 30.0,
|
| 481 |
+
"eval_loss": 0.4880525767803192,
|
| 482 |
+
"eval_mae": 0.5353544354438782,
|
| 483 |
+
"eval_mse": 0.4880525767803192,
|
| 484 |
+
"eval_rmse": 0.6986076235771179,
|
| 485 |
+
"eval_runtime": 1.2654,
|
| 486 |
+
"eval_samples_per_second": 331.922,
|
| 487 |
+
"eval_steps_per_second": 41.885,
|
| 488 |
+
"step": 12600
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 30.95,
|
| 492 |
+
"learning_rate": 3.80952380952381e-06,
|
| 493 |
+
"loss": 0.0404,
|
| 494 |
+
"step": 13000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 31.0,
|
| 498 |
+
"eval_loss": 0.48999953269958496,
|
| 499 |
+
"eval_mae": 0.5326849222183228,
|
| 500 |
+
"eval_mse": 0.4899995028972626,
|
| 501 |
+
"eval_rmse": 0.6999996304512024,
|
| 502 |
+
"eval_runtime": 1.2442,
|
| 503 |
+
"eval_samples_per_second": 337.554,
|
| 504 |
+
"eval_steps_per_second": 42.596,
|
| 505 |
+
"step": 13020
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 32.0,
|
| 509 |
+
"eval_loss": 0.5017576813697815,
|
| 510 |
+
"eval_mae": 0.5423673987388611,
|
| 511 |
+
"eval_mse": 0.5017576813697815,
|
| 512 |
+
"eval_rmse": 0.7083485722541809,
|
| 513 |
+
"eval_runtime": 1.1196,
|
| 514 |
+
"eval_samples_per_second": 375.135,
|
| 515 |
+
"eval_steps_per_second": 47.339,
|
| 516 |
+
"step": 13440
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 32.14,
|
| 520 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 521 |
+
"loss": 0.0391,
|
| 522 |
+
"step": 13500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 33.0,
|
| 526 |
+
"eval_loss": 0.48715752363204956,
|
| 527 |
+
"eval_mae": 0.5341249108314514,
|
| 528 |
+
"eval_mse": 0.48715752363204956,
|
| 529 |
+
"eval_rmse": 0.6979666948318481,
|
| 530 |
+
"eval_runtime": 1.1228,
|
| 531 |
+
"eval_samples_per_second": 374.062,
|
| 532 |
+
"eval_steps_per_second": 47.203,
|
| 533 |
+
"step": 13860
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 33.33,
|
| 537 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 538 |
+
"loss": 0.0373,
|
| 539 |
+
"step": 14000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 34.0,
|
| 543 |
+
"eval_loss": 0.479116827249527,
|
| 544 |
+
"eval_mae": 0.5321008563041687,
|
| 545 |
+
"eval_mse": 0.479116827249527,
|
| 546 |
+
"eval_rmse": 0.6921826601028442,
|
| 547 |
+
"eval_runtime": 1.206,
|
| 548 |
+
"eval_samples_per_second": 348.254,
|
| 549 |
+
"eval_steps_per_second": 43.946,
|
| 550 |
+
"step": 14280
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 34.52,
|
| 554 |
+
"learning_rate": 3.0952380952380957e-06,
|
| 555 |
+
"loss": 0.0359,
|
| 556 |
+
"step": 14500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 35.0,
|
| 560 |
+
"eval_loss": 0.48590707778930664,
|
| 561 |
+
"eval_mae": 0.5346122980117798,
|
| 562 |
+
"eval_mse": 0.48590704798698425,
|
| 563 |
+
"eval_rmse": 0.6970703601837158,
|
| 564 |
+
"eval_runtime": 0.8892,
|
| 565 |
+
"eval_samples_per_second": 472.339,
|
| 566 |
+
"eval_steps_per_second": 59.605,
|
| 567 |
+
"step": 14700
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 35.71,
|
| 571 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 572 |
+
"loss": 0.0334,
|
| 573 |
+
"step": 15000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 36.0,
|
| 577 |
+
"eval_loss": 0.4766678810119629,
|
| 578 |
+
"eval_mae": 0.5263535380363464,
|
| 579 |
+
"eval_mse": 0.4766678810119629,
|
| 580 |
+
"eval_rmse": 0.690411388874054,
|
| 581 |
+
"eval_runtime": 1.286,
|
| 582 |
+
"eval_samples_per_second": 326.603,
|
| 583 |
+
"eval_steps_per_second": 41.214,
|
| 584 |
+
"step": 15120
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 36.9,
|
| 588 |
+
"learning_rate": 2.6190476190476192e-06,
|
| 589 |
+
"loss": 0.0341,
|
| 590 |
+
"step": 15500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 37.0,
|
| 594 |
+
"eval_loss": 0.4740683436393738,
|
| 595 |
+
"eval_mae": 0.5217899680137634,
|
| 596 |
+
"eval_mse": 0.4740683138370514,
|
| 597 |
+
"eval_rmse": 0.6885262131690979,
|
| 598 |
+
"eval_runtime": 1.1893,
|
| 599 |
+
"eval_samples_per_second": 353.162,
|
| 600 |
+
"eval_steps_per_second": 44.566,
|
| 601 |
+
"step": 15540
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 38.0,
|
| 605 |
+
"eval_loss": 0.478584349155426,
|
| 606 |
+
"eval_mae": 0.527285635471344,
|
| 607 |
+
"eval_mse": 0.478584349155426,
|
| 608 |
+
"eval_rmse": 0.6917979121208191,
|
| 609 |
+
"eval_runtime": 1.1477,
|
| 610 |
+
"eval_samples_per_second": 365.939,
|
| 611 |
+
"eval_steps_per_second": 46.178,
|
| 612 |
+
"step": 15960
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 38.1,
|
| 616 |
+
"learning_rate": 2.380952380952381e-06,
|
| 617 |
+
"loss": 0.0325,
|
| 618 |
+
"step": 16000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 39.0,
|
| 622 |
+
"eval_loss": 0.46834418177604675,
|
| 623 |
+
"eval_mae": 0.5196450352668762,
|
| 624 |
+
"eval_mse": 0.46834418177604675,
|
| 625 |
+
"eval_rmse": 0.6843567490577698,
|
| 626 |
+
"eval_runtime": 1.1282,
|
| 627 |
+
"eval_samples_per_second": 372.276,
|
| 628 |
+
"eval_steps_per_second": 46.978,
|
| 629 |
+
"step": 16380
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 39.29,
|
| 633 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 634 |
+
"loss": 0.0331,
|
| 635 |
+
"step": 16500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 40.0,
|
| 639 |
+
"eval_loss": 0.46904683113098145,
|
| 640 |
+
"eval_mae": 0.522687554359436,
|
| 641 |
+
"eval_mse": 0.46904683113098145,
|
| 642 |
+
"eval_rmse": 0.6848699450492859,
|
| 643 |
+
"eval_runtime": 1.1578,
|
| 644 |
+
"eval_samples_per_second": 362.764,
|
| 645 |
+
"eval_steps_per_second": 45.777,
|
| 646 |
+
"step": 16800
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 40.48,
|
| 650 |
+
"learning_rate": 1.904761904761905e-06,
|
| 651 |
+
"loss": 0.0315,
|
| 652 |
+
"step": 17000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 41.0,
|
| 656 |
+
"eval_loss": 0.46947211027145386,
|
| 657 |
+
"eval_mae": 0.5197708010673523,
|
| 658 |
+
"eval_mse": 0.46947211027145386,
|
| 659 |
+
"eval_rmse": 0.6851803660392761,
|
| 660 |
+
"eval_runtime": 1.1711,
|
| 661 |
+
"eval_samples_per_second": 358.64,
|
| 662 |
+
"eval_steps_per_second": 45.257,
|
| 663 |
+
"step": 17220
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 41.67,
|
| 667 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 668 |
+
"loss": 0.0299,
|
| 669 |
+
"step": 17500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 42.0,
|
| 673 |
+
"eval_loss": 0.46514230966567993,
|
| 674 |
+
"eval_mae": 0.518059253692627,
|
| 675 |
+
"eval_mse": 0.46514227986335754,
|
| 676 |
+
"eval_rmse": 0.6820133924484253,
|
| 677 |
+
"eval_runtime": 1.1482,
|
| 678 |
+
"eval_samples_per_second": 365.797,
|
| 679 |
+
"eval_steps_per_second": 46.16,
|
| 680 |
+
"step": 17640
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 42.86,
|
| 684 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 685 |
+
"loss": 0.0314,
|
| 686 |
+
"step": 18000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 43.0,
|
| 690 |
+
"eval_loss": 0.4640100300312042,
|
| 691 |
+
"eval_mae": 0.51801997423172,
|
| 692 |
+
"eval_mse": 0.46400997042655945,
|
| 693 |
+
"eval_rmse": 0.6811828017234802,
|
| 694 |
+
"eval_runtime": 1.1908,
|
| 695 |
+
"eval_samples_per_second": 352.696,
|
| 696 |
+
"eval_steps_per_second": 44.507,
|
| 697 |
+
"step": 18060
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 44.0,
|
| 701 |
+
"eval_loss": 0.4704785943031311,
|
| 702 |
+
"eval_mae": 0.5230998992919922,
|
| 703 |
+
"eval_mse": 0.4704785943031311,
|
| 704 |
+
"eval_rmse": 0.6859143972396851,
|
| 705 |
+
"eval_runtime": 1.2463,
|
| 706 |
+
"eval_samples_per_second": 337.011,
|
| 707 |
+
"eval_steps_per_second": 42.528,
|
| 708 |
+
"step": 18480
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 44.05,
|
| 712 |
+
"learning_rate": 1.1904761904761906e-06,
|
| 713 |
+
"loss": 0.0283,
|
| 714 |
+
"step": 18500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 45.0,
|
| 718 |
+
"eval_loss": 0.4678580164909363,
|
| 719 |
+
"eval_mae": 0.521861732006073,
|
| 720 |
+
"eval_mse": 0.46785807609558105,
|
| 721 |
+
"eval_rmse": 0.6840015053749084,
|
| 722 |
+
"eval_runtime": 1.2433,
|
| 723 |
+
"eval_samples_per_second": 337.812,
|
| 724 |
+
"eval_steps_per_second": 42.629,
|
| 725 |
+
"step": 18900
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 45.24,
|
| 729 |
+
"learning_rate": 9.523809523809525e-07,
|
| 730 |
+
"loss": 0.0284,
|
| 731 |
+
"step": 19000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 46.0,
|
| 735 |
+
"eval_loss": 0.4686986207962036,
|
| 736 |
+
"eval_mae": 0.5229542851448059,
|
| 737 |
+
"eval_mse": 0.4686986207962036,
|
| 738 |
+
"eval_rmse": 0.6846156716346741,
|
| 739 |
+
"eval_runtime": 1.1892,
|
| 740 |
+
"eval_samples_per_second": 353.193,
|
| 741 |
+
"eval_steps_per_second": 44.57,
|
| 742 |
+
"step": 19320
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 46.43,
|
| 746 |
+
"learning_rate": 7.142857142857143e-07,
|
| 747 |
+
"loss": 0.0273,
|
| 748 |
+
"step": 19500
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 47.0,
|
| 752 |
+
"eval_loss": 0.46382173895835876,
|
| 753 |
+
"eval_mae": 0.5197833776473999,
|
| 754 |
+
"eval_mse": 0.4638217091560364,
|
| 755 |
+
"eval_rmse": 0.6810445785522461,
|
| 756 |
+
"eval_runtime": 1.2872,
|
| 757 |
+
"eval_samples_per_second": 326.279,
|
| 758 |
+
"eval_steps_per_second": 41.173,
|
| 759 |
+
"step": 19740
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 47.62,
|
| 763 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 764 |
+
"loss": 0.0283,
|
| 765 |
+
"step": 20000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 48.0,
|
| 769 |
+
"eval_loss": 0.4631454348564148,
|
| 770 |
+
"eval_mae": 0.5184262990951538,
|
| 771 |
+
"eval_mse": 0.4631454348564148,
|
| 772 |
+
"eval_rmse": 0.6805478930473328,
|
| 773 |
+
"eval_runtime": 1.1721,
|
| 774 |
+
"eval_samples_per_second": 358.345,
|
| 775 |
+
"eval_steps_per_second": 45.22,
|
| 776 |
+
"step": 20160
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 48.81,
|
| 780 |
+
"learning_rate": 2.3809523809523811e-07,
|
| 781 |
+
"loss": 0.0268,
|
| 782 |
+
"step": 20500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 49.0,
|
| 786 |
+
"eval_loss": 0.4649342894554138,
|
| 787 |
+
"eval_mae": 0.5196540355682373,
|
| 788 |
+
"eval_mse": 0.4649342894554138,
|
| 789 |
+
"eval_rmse": 0.6818609237670898,
|
| 790 |
+
"eval_runtime": 1.1402,
|
| 791 |
+
"eval_samples_per_second": 368.356,
|
| 792 |
+
"eval_steps_per_second": 46.483,
|
| 793 |
+
"step": 20580
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 50.0,
|
| 797 |
+
"learning_rate": 0.0,
|
| 798 |
+
"loss": 0.0269,
|
| 799 |
+
"step": 21000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 50.0,
|
| 803 |
+
"eval_loss": 0.46444272994995117,
|
| 804 |
+
"eval_mae": 0.5188572406768799,
|
| 805 |
+
"eval_mse": 0.46444275975227356,
|
| 806 |
+
"eval_rmse": 0.6815003752708435,
|
| 807 |
+
"eval_runtime": 1.0966,
|
| 808 |
+
"eval_samples_per_second": 382.987,
|
| 809 |
+
"eval_steps_per_second": 48.329,
|
| 810 |
+
"step": 21000
|
| 811 |
+
}
|
| 812 |
+
],
|
| 813 |
+
"max_steps": 21000,
|
| 814 |
+
"num_train_epochs": 50,
|
| 815 |
+
"total_flos": 1.1126765647872e+16,
|
| 816 |
+
"trial_name": null,
|
| 817 |
+
"trial_params": null
|
| 818 |
+
}
|
checkpoint-21000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28de34ee8013d54b9b537082795de541af9b7e6264c92b19a1cb5e5e3df7cfdb
|
| 3 |
+
size 2927
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/saved_models/our_90epochs_saved_model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSelfiesClassification"
|
| 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": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 514,
|
| 23 |
+
"model_type": "roberta",
|
| 24 |
+
"num_attention_heads": 4,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"pad_token_id": 1,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.15.0",
|
| 30 |
+
"type_vocab_size": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 800
|
| 33 |
+
}
|
lipo.out
ADDED
|
@@ -0,0 +1,472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Some weights of the model checkpoint at data/saved_models/our_90epochs_saved_model were not used when initializing RobertaForSelfiesClassification: ['lm_head.bias', 'lm_head.dense.bias', 'lm_head.layer_norm.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.weight']
|
| 2 |
+
- This IS expected if you are initializing RobertaForSelfiesClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
|
| 3 |
+
- This IS NOT expected if you are initializing RobertaForSelfiesClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
|
| 4 |
+
Some weights of RobertaForSelfiesClassification were not initialized from the model checkpoint at data/saved_models/our_90epochs_saved_model and are newly initialized: ['classifier.out_proj.bias', 'roberta.pooler.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.weight', 'roberta.pooler.dense.weight', 'classifier.dense.bias']
|
| 5 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 6 |
+
Not using a scaler.
|
| 7 |
+
***** Running training *****
|
| 8 |
+
Num examples = 3360
|
| 9 |
+
Num Epochs = 50
|
| 10 |
+
Instantaneous batch size per device = 8
|
| 11 |
+
Total train batch size (w. parallel, distributed & accumulation) = 8
|
| 12 |
+
Gradient Accumulation steps = 1
|
| 13 |
+
Total optimization steps = 21000
|
| 14 |
+
***** Running Evaluation *****
|
| 15 |
+
Num examples = 420
|
| 16 |
+
Batch size = 8
|
| 17 |
+
{'eval_loss': 0.7975520491600037, 'eval_mse': 0.7975521087646484, 'eval_rmse': 0.8930577039718628, 'eval_mae': 0.7266795039176941, 'eval_runtime': 2.2756, 'eval_samples_per_second': 184.568, 'eval_steps_per_second': 23.291, 'epoch': 1.0}
|
| 18 |
+
Saving model checkpoint to our_lipo_model/checkpoint-420
|
| 19 |
+
Configuration saved in our_lipo_model/checkpoint-420/config.json
|
| 20 |
+
Model weights saved in our_lipo_model/checkpoint-420/pytorch_model.bin
|
| 21 |
+
{'loss': 1.111, 'learning_rate': 9.761904761904762e-06, 'epoch': 1.19}
|
| 22 |
+
***** Running Evaluation *****
|
| 23 |
+
Num examples = 420
|
| 24 |
+
Batch size = 8
|
| 25 |
+
{'eval_loss': 0.609792947769165, 'eval_mse': 0.609792947769165, 'eval_rmse': 0.7808924317359924, 'eval_mae': 0.6158387660980225, 'eval_runtime': 1.9303, 'eval_samples_per_second': 217.582, 'eval_steps_per_second': 27.457, 'epoch': 2.0}
|
| 26 |
+
Saving model checkpoint to our_lipo_model/checkpoint-840
|
| 27 |
+
Configuration saved in our_lipo_model/checkpoint-840/config.json
|
| 28 |
+
Model weights saved in our_lipo_model/checkpoint-840/pytorch_model.bin
|
| 29 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-420] due to args.save_total_limit
|
| 30 |
+
{'loss': 0.4808, 'learning_rate': 9.523809523809525e-06, 'epoch': 2.38}
|
| 31 |
+
***** Running Evaluation *****
|
| 32 |
+
Num examples = 420
|
| 33 |
+
Batch size = 8
|
| 34 |
+
{'eval_loss': 0.6106507182121277, 'eval_mse': 0.6106507778167725, 'eval_rmse': 0.7814414501190186, 'eval_mae': 0.5975062847137451, 'eval_runtime': 2.7602, 'eval_samples_per_second': 152.163, 'eval_steps_per_second': 19.202, 'epoch': 3.0}
|
| 35 |
+
Saving model checkpoint to our_lipo_model/checkpoint-1260
|
| 36 |
+
Configuration saved in our_lipo_model/checkpoint-1260/config.json
|
| 37 |
+
Model weights saved in our_lipo_model/checkpoint-1260/pytorch_model.bin
|
| 38 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-840] due to args.save_total_limit
|
| 39 |
+
{'loss': 0.3196, 'learning_rate': 9.285714285714288e-06, 'epoch': 3.57}
|
| 40 |
+
***** Running Evaluation *****
|
| 41 |
+
Num examples = 420
|
| 42 |
+
Batch size = 8
|
| 43 |
+
{'eval_loss': 0.5748845338821411, 'eval_mse': 0.5748845934867859, 'eval_rmse': 0.7582114338874817, 'eval_mae': 0.584411084651947, 'eval_runtime': 1.9617, 'eval_samples_per_second': 214.099, 'eval_steps_per_second': 27.017, 'epoch': 4.0}
|
| 44 |
+
Saving model checkpoint to our_lipo_model/checkpoint-1680
|
| 45 |
+
Configuration saved in our_lipo_model/checkpoint-1680/config.json
|
| 46 |
+
Model weights saved in our_lipo_model/checkpoint-1680/pytorch_model.bin
|
| 47 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-1260] due to args.save_total_limit
|
| 48 |
+
{'loss': 0.2357, 'learning_rate': 9.047619047619049e-06, 'epoch': 4.76}
|
| 49 |
+
***** Running Evaluation *****
|
| 50 |
+
Num examples = 420
|
| 51 |
+
Batch size = 8
|
| 52 |
+
{'eval_loss': 0.6165366172790527, 'eval_mse': 0.6165366172790527, 'eval_rmse': 0.785198450088501, 'eval_mae': 0.5906195640563965, 'eval_runtime': 2.7689, 'eval_samples_per_second': 151.687, 'eval_steps_per_second': 19.141, 'epoch': 5.0}
|
| 53 |
+
Saving model checkpoint to our_lipo_model/checkpoint-2100
|
| 54 |
+
Configuration saved in our_lipo_model/checkpoint-2100/config.json
|
| 55 |
+
Model weights saved in our_lipo_model/checkpoint-2100/pytorch_model.bin
|
| 56 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-1680] due to args.save_total_limit
|
| 57 |
+
{'loss': 0.1909, 'learning_rate': 8.80952380952381e-06, 'epoch': 5.95}
|
| 58 |
+
***** Running Evaluation *****
|
| 59 |
+
Num examples = 420
|
| 60 |
+
Batch size = 8
|
| 61 |
+
{'eval_loss': 0.5579051375389099, 'eval_mse': 0.5579050779342651, 'eval_rmse': 0.7469304203987122, 'eval_mae': 0.5814845561981201, 'eval_runtime': 1.2975, 'eval_samples_per_second': 323.7, 'eval_steps_per_second': 40.848, 'epoch': 6.0}
|
| 62 |
+
Saving model checkpoint to our_lipo_model/checkpoint-2520
|
| 63 |
+
Configuration saved in our_lipo_model/checkpoint-2520/config.json
|
| 64 |
+
Model weights saved in our_lipo_model/checkpoint-2520/pytorch_model.bin
|
| 65 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-2100] due to args.save_total_limit
|
| 66 |
+
***** Running Evaluation *****
|
| 67 |
+
Num examples = 420
|
| 68 |
+
Batch size = 8
|
| 69 |
+
{'eval_loss': 0.5374110341072083, 'eval_mse': 0.5374110341072083, 'eval_rmse': 0.7330832481384277, 'eval_mae': 0.5643972754478455, 'eval_runtime': 2.8385, 'eval_samples_per_second': 147.967, 'eval_steps_per_second': 18.672, 'epoch': 7.0}
|
| 70 |
+
Saving model checkpoint to our_lipo_model/checkpoint-2940
|
| 71 |
+
Configuration saved in our_lipo_model/checkpoint-2940/config.json
|
| 72 |
+
Model weights saved in our_lipo_model/checkpoint-2940/pytorch_model.bin
|
| 73 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-2520] due to args.save_total_limit
|
| 74 |
+
{'loss': 0.157, 'learning_rate': 8.571428571428571e-06, 'epoch': 7.14}
|
| 75 |
+
***** Running Evaluation *****
|
| 76 |
+
Num examples = 420
|
| 77 |
+
Batch size = 8
|
| 78 |
+
{'eval_loss': 0.5414829850196838, 'eval_mse': 0.5414829254150391, 'eval_rmse': 0.735855221748352, 'eval_mae': 0.5653696060180664, 'eval_runtime': 2.0614, 'eval_samples_per_second': 203.747, 'eval_steps_per_second': 25.711, 'epoch': 8.0}
|
| 79 |
+
Saving model checkpoint to our_lipo_model/checkpoint-3360
|
| 80 |
+
Configuration saved in our_lipo_model/checkpoint-3360/config.json
|
| 81 |
+
Model weights saved in our_lipo_model/checkpoint-3360/pytorch_model.bin
|
| 82 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-2940] due to args.save_total_limit
|
| 83 |
+
{'loss': 0.1334, 'learning_rate': 8.333333333333334e-06, 'epoch': 8.33}
|
| 84 |
+
***** Running Evaluation *****
|
| 85 |
+
Num examples = 420
|
| 86 |
+
Batch size = 8
|
| 87 |
+
{'eval_loss': 0.5609115958213806, 'eval_mse': 0.5609115362167358, 'eval_rmse': 0.7489402890205383, 'eval_mae': 0.5715270042419434, 'eval_runtime': 1.9712, 'eval_samples_per_second': 213.066, 'eval_steps_per_second': 26.887, 'epoch': 9.0}
|
| 88 |
+
Saving model checkpoint to our_lipo_model/checkpoint-3780
|
| 89 |
+
Configuration saved in our_lipo_model/checkpoint-3780/config.json
|
| 90 |
+
Model weights saved in our_lipo_model/checkpoint-3780/pytorch_model.bin
|
| 91 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-3360] due to args.save_total_limit
|
| 92 |
+
{'loss': 0.1199, 'learning_rate': 8.095238095238097e-06, 'epoch': 9.52}
|
| 93 |
+
***** Running Evaluation *****
|
| 94 |
+
Num examples = 420
|
| 95 |
+
Batch size = 8
|
| 96 |
+
{'eval_loss': 0.5141286253929138, 'eval_mse': 0.5141286253929138, 'eval_rmse': 0.7170276045799255, 'eval_mae': 0.5450649261474609, 'eval_runtime': 1.9528, 'eval_samples_per_second': 215.081, 'eval_steps_per_second': 27.141, 'epoch': 10.0}
|
| 97 |
+
Saving model checkpoint to our_lipo_model/checkpoint-4200
|
| 98 |
+
Configuration saved in our_lipo_model/checkpoint-4200/config.json
|
| 99 |
+
Model weights saved in our_lipo_model/checkpoint-4200/pytorch_model.bin
|
| 100 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-3780] due to args.save_total_limit
|
| 101 |
+
{'loss': 0.1112, 'learning_rate': 7.857142857142858e-06, 'epoch': 10.71}
|
| 102 |
+
***** Running Evaluation *****
|
| 103 |
+
Num examples = 420
|
| 104 |
+
Batch size = 8
|
| 105 |
+
{'eval_loss': 0.5070027112960815, 'eval_mse': 0.5070027112960815, 'eval_rmse': 0.7120411992073059, 'eval_mae': 0.5421043634414673, 'eval_runtime': 1.3515, 'eval_samples_per_second': 310.772, 'eval_steps_per_second': 39.216, 'epoch': 11.0}
|
| 106 |
+
Saving model checkpoint to our_lipo_model/checkpoint-4620
|
| 107 |
+
Configuration saved in our_lipo_model/checkpoint-4620/config.json
|
| 108 |
+
Model weights saved in our_lipo_model/checkpoint-4620/pytorch_model.bin
|
| 109 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-4200] due to args.save_total_limit
|
| 110 |
+
{'loss': 0.0983, 'learning_rate': 7.61904761904762e-06, 'epoch': 11.9}
|
| 111 |
+
***** Running Evaluation *****
|
| 112 |
+
Num examples = 420
|
| 113 |
+
Batch size = 8
|
| 114 |
+
{'eval_loss': 0.5180405378341675, 'eval_mse': 0.5180405378341675, 'eval_rmse': 0.7197503447532654, 'eval_mae': 0.5500118732452393, 'eval_runtime': 1.2448, 'eval_samples_per_second': 337.399, 'eval_steps_per_second': 42.577, 'epoch': 12.0}
|
| 115 |
+
Saving model checkpoint to our_lipo_model/checkpoint-5040
|
| 116 |
+
Configuration saved in our_lipo_model/checkpoint-5040/config.json
|
| 117 |
+
Model weights saved in our_lipo_model/checkpoint-5040/pytorch_model.bin
|
| 118 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-4620] due to args.save_total_limit
|
| 119 |
+
***** Running Evaluation *****
|
| 120 |
+
Num examples = 420
|
| 121 |
+
Batch size = 8
|
| 122 |
+
{'eval_loss': 0.5257736444473267, 'eval_mse': 0.5257736444473267, 'eval_rmse': 0.7251024842262268, 'eval_mae': 0.561431348323822, 'eval_runtime': 1.1775, 'eval_samples_per_second': 356.675, 'eval_steps_per_second': 45.009, 'epoch': 13.0}
|
| 123 |
+
Saving model checkpoint to our_lipo_model/checkpoint-5460
|
| 124 |
+
Configuration saved in our_lipo_model/checkpoint-5460/config.json
|
| 125 |
+
Model weights saved in our_lipo_model/checkpoint-5460/pytorch_model.bin
|
| 126 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-5040] due to args.save_total_limit
|
| 127 |
+
{'loss': 0.0861, 'learning_rate': 7.380952380952382e-06, 'epoch': 13.1}
|
| 128 |
+
***** Running Evaluation *****
|
| 129 |
+
Num examples = 420
|
| 130 |
+
Batch size = 8
|
| 131 |
+
{'eval_loss': 0.5195261836051941, 'eval_mse': 0.5195261836051941, 'eval_rmse': 0.7207816243171692, 'eval_mae': 0.5508889555931091, 'eval_runtime': 1.2061, 'eval_samples_per_second': 348.216, 'eval_steps_per_second': 43.942, 'epoch': 14.0}
|
| 132 |
+
Saving model checkpoint to our_lipo_model/checkpoint-5880
|
| 133 |
+
Configuration saved in our_lipo_model/checkpoint-5880/config.json
|
| 134 |
+
Model weights saved in our_lipo_model/checkpoint-5880/pytorch_model.bin
|
| 135 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-5460] due to args.save_total_limit
|
| 136 |
+
{'loss': 0.0833, 'learning_rate': 7.1428571428571436e-06, 'epoch': 14.29}
|
| 137 |
+
***** Running Evaluation *****
|
| 138 |
+
Num examples = 420
|
| 139 |
+
Batch size = 8
|
| 140 |
+
{'eval_loss': 0.5224341154098511, 'eval_mse': 0.5224341154098511, 'eval_rmse': 0.7227960228919983, 'eval_mae': 0.552178144454956, 'eval_runtime': 1.1671, 'eval_samples_per_second': 359.858, 'eval_steps_per_second': 45.411, 'epoch': 15.0}
|
| 141 |
+
Saving model checkpoint to our_lipo_model/checkpoint-6300
|
| 142 |
+
Configuration saved in our_lipo_model/checkpoint-6300/config.json
|
| 143 |
+
Model weights saved in our_lipo_model/checkpoint-6300/pytorch_model.bin
|
| 144 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-5880] due to args.save_total_limit
|
| 145 |
+
{'loss': 0.0741, 'learning_rate': 6.9047619047619055e-06, 'epoch': 15.48}
|
| 146 |
+
***** Running Evaluation *****
|
| 147 |
+
Num examples = 420
|
| 148 |
+
Batch size = 8
|
| 149 |
+
{'eval_loss': 0.5121651291847229, 'eval_mse': 0.5121651291847229, 'eval_rmse': 0.715657114982605, 'eval_mae': 0.5470804572105408, 'eval_runtime': 1.1174, 'eval_samples_per_second': 375.865, 'eval_steps_per_second': 47.431, 'epoch': 16.0}
|
| 150 |
+
Saving model checkpoint to our_lipo_model/checkpoint-6720
|
| 151 |
+
Configuration saved in our_lipo_model/checkpoint-6720/config.json
|
| 152 |
+
Model weights saved in our_lipo_model/checkpoint-6720/pytorch_model.bin
|
| 153 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-6300] due to args.save_total_limit
|
| 154 |
+
{'loss': 0.0744, 'learning_rate': 6.666666666666667e-06, 'epoch': 16.67}
|
| 155 |
+
***** Running Evaluation *****
|
| 156 |
+
Num examples = 420
|
| 157 |
+
Batch size = 8
|
| 158 |
+
{'eval_loss': 0.4920870065689087, 'eval_mse': 0.4920870065689087, 'eval_rmse': 0.7014891505241394, 'eval_mae': 0.5328148007392883, 'eval_runtime': 1.1494, 'eval_samples_per_second': 365.42, 'eval_steps_per_second': 46.112, 'epoch': 17.0}
|
| 159 |
+
Saving model checkpoint to our_lipo_model/checkpoint-7140
|
| 160 |
+
Configuration saved in our_lipo_model/checkpoint-7140/config.json
|
| 161 |
+
Model weights saved in our_lipo_model/checkpoint-7140/pytorch_model.bin
|
| 162 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-6720] due to args.save_total_limit
|
| 163 |
+
{'loss': 0.0649, 'learning_rate': 6.4285714285714295e-06, 'epoch': 17.86}
|
| 164 |
+
***** Running Evaluation *****
|
| 165 |
+
Num examples = 420
|
| 166 |
+
Batch size = 8
|
| 167 |
+
{'eval_loss': 0.5028687119483948, 'eval_mse': 0.5028687119483948, 'eval_rmse': 0.7091323733329773, 'eval_mae': 0.5357252359390259, 'eval_runtime': 1.3327, 'eval_samples_per_second': 315.156, 'eval_steps_per_second': 39.77, 'epoch': 18.0}
|
| 168 |
+
Saving model checkpoint to our_lipo_model/checkpoint-7560
|
| 169 |
+
Configuration saved in our_lipo_model/checkpoint-7560/config.json
|
| 170 |
+
Model weights saved in our_lipo_model/checkpoint-7560/pytorch_model.bin
|
| 171 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-7140] due to args.save_total_limit
|
| 172 |
+
***** Running Evaluation *****
|
| 173 |
+
Num examples = 420
|
| 174 |
+
Batch size = 8
|
| 175 |
+
{'eval_loss': 0.526236891746521, 'eval_mse': 0.526236891746521, 'eval_rmse': 0.7254218459129333, 'eval_mae': 0.5603699684143066, 'eval_runtime': 1.2696, 'eval_samples_per_second': 330.822, 'eval_steps_per_second': 41.747, 'epoch': 19.0}
|
| 176 |
+
Saving model checkpoint to our_lipo_model/checkpoint-7980
|
| 177 |
+
Configuration saved in our_lipo_model/checkpoint-7980/config.json
|
| 178 |
+
Model weights saved in our_lipo_model/checkpoint-7980/pytorch_model.bin
|
| 179 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-7560] due to args.save_total_limit
|
| 180 |
+
{'loss': 0.0639, 'learning_rate': 6.1904761904761914e-06, 'epoch': 19.05}
|
| 181 |
+
***** Running Evaluation *****
|
| 182 |
+
Num examples = 420
|
| 183 |
+
Batch size = 8
|
| 184 |
+
{'eval_loss': 0.5124732851982117, 'eval_mse': 0.5124732851982117, 'eval_rmse': 0.7158724069595337, 'eval_mae': 0.5440532565116882, 'eval_runtime': 1.139, 'eval_samples_per_second': 368.742, 'eval_steps_per_second': 46.532, 'epoch': 20.0}
|
| 185 |
+
Saving model checkpoint to our_lipo_model/checkpoint-8400
|
| 186 |
+
Configuration saved in our_lipo_model/checkpoint-8400/config.json
|
| 187 |
+
Model weights saved in our_lipo_model/checkpoint-8400/pytorch_model.bin
|
| 188 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-7980] due to args.save_total_limit
|
| 189 |
+
{'loss': 0.0609, 'learning_rate': 5.9523809523809525e-06, 'epoch': 20.24}
|
| 190 |
+
***** Running Evaluation *****
|
| 191 |
+
Num examples = 420
|
| 192 |
+
Batch size = 8
|
| 193 |
+
{'eval_loss': 0.4891616106033325, 'eval_mse': 0.48916158080101013, 'eval_rmse': 0.6994009017944336, 'eval_mae': 0.5339100956916809, 'eval_runtime': 1.0834, 'eval_samples_per_second': 387.673, 'eval_steps_per_second': 48.921, 'epoch': 21.0}
|
| 194 |
+
Saving model checkpoint to our_lipo_model/checkpoint-8820
|
| 195 |
+
Configuration saved in our_lipo_model/checkpoint-8820/config.json
|
| 196 |
+
Model weights saved in our_lipo_model/checkpoint-8820/pytorch_model.bin
|
| 197 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-8400] due to args.save_total_limit
|
| 198 |
+
{'loss': 0.0547, 'learning_rate': 5.7142857142857145e-06, 'epoch': 21.43}
|
| 199 |
+
***** Running Evaluation *****
|
| 200 |
+
Num examples = 420
|
| 201 |
+
Batch size = 8
|
| 202 |
+
{'eval_loss': 0.4973764717578888, 'eval_mse': 0.4973764419555664, 'eval_rmse': 0.7052491903305054, 'eval_mae': 0.5337387919425964, 'eval_runtime': 1.1768, 'eval_samples_per_second': 356.886, 'eval_steps_per_second': 45.036, 'epoch': 22.0}
|
| 203 |
+
Saving model checkpoint to our_lipo_model/checkpoint-9240
|
| 204 |
+
Configuration saved in our_lipo_model/checkpoint-9240/config.json
|
| 205 |
+
Model weights saved in our_lipo_model/checkpoint-9240/pytorch_model.bin
|
| 206 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-8820] due to args.save_total_limit
|
| 207 |
+
{'loss': 0.0528, 'learning_rate': 5.476190476190477e-06, 'epoch': 22.62}
|
| 208 |
+
***** Running Evaluation *****
|
| 209 |
+
Num examples = 420
|
| 210 |
+
Batch size = 8
|
| 211 |
+
{'eval_loss': 0.4779137670993805, 'eval_mse': 0.47791385650634766, 'eval_rmse': 0.6913131475448608, 'eval_mae': 0.5240978598594666, 'eval_runtime': 1.1884, 'eval_samples_per_second': 353.429, 'eval_steps_per_second': 44.599, 'epoch': 23.0}
|
| 212 |
+
Saving model checkpoint to our_lipo_model/checkpoint-9660
|
| 213 |
+
Configuration saved in our_lipo_model/checkpoint-9660/config.json
|
| 214 |
+
Model weights saved in our_lipo_model/checkpoint-9660/pytorch_model.bin
|
| 215 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-9240] due to args.save_total_limit
|
| 216 |
+
{'loss': 0.0514, 'learning_rate': 5.2380952380952384e-06, 'epoch': 23.81}
|
| 217 |
+
***** Running Evaluation *****
|
| 218 |
+
Num examples = 420
|
| 219 |
+
Batch size = 8
|
| 220 |
+
{'eval_loss': 0.483572781085968, 'eval_mse': 0.48357275128364563, 'eval_rmse': 0.695393979549408, 'eval_mae': 0.5290801525115967, 'eval_runtime': 1.1926, 'eval_samples_per_second': 352.184, 'eval_steps_per_second': 44.442, 'epoch': 24.0}
|
| 221 |
+
Saving model checkpoint to our_lipo_model/checkpoint-10080
|
| 222 |
+
Configuration saved in our_lipo_model/checkpoint-10080/config.json
|
| 223 |
+
Model weights saved in our_lipo_model/checkpoint-10080/pytorch_model.bin
|
| 224 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-9660] due to args.save_total_limit
|
| 225 |
+
{'loss': 0.0516, 'learning_rate': 5e-06, 'epoch': 25.0}
|
| 226 |
+
***** Running Evaluation *****
|
| 227 |
+
Num examples = 420
|
| 228 |
+
Batch size = 8
|
| 229 |
+
{'eval_loss': 0.4979321360588074, 'eval_mse': 0.49793222546577454, 'eval_rmse': 0.7056431174278259, 'eval_mae': 0.5313663482666016, 'eval_runtime': 1.1676, 'eval_samples_per_second': 359.71, 'eval_steps_per_second': 45.392, 'epoch': 25.0}
|
| 230 |
+
Saving model checkpoint to our_lipo_model/checkpoint-10500
|
| 231 |
+
Configuration saved in our_lipo_model/checkpoint-10500/config.json
|
| 232 |
+
Model weights saved in our_lipo_model/checkpoint-10500/pytorch_model.bin
|
| 233 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-10080] due to args.save_total_limit
|
| 234 |
+
***** Running Evaluation *****
|
| 235 |
+
Num examples = 420
|
| 236 |
+
Batch size = 8
|
| 237 |
+
{'eval_loss': 0.48045653104782104, 'eval_mse': 0.48045653104782104, 'eval_rmse': 0.693149745464325, 'eval_mae': 0.530644416809082, 'eval_runtime': 1.1924, 'eval_samples_per_second': 352.222, 'eval_steps_per_second': 44.447, 'epoch': 26.0}
|
| 238 |
+
Saving model checkpoint to our_lipo_model/checkpoint-10920
|
| 239 |
+
Configuration saved in our_lipo_model/checkpoint-10920/config.json
|
| 240 |
+
Model weights saved in our_lipo_model/checkpoint-10920/pytorch_model.bin
|
| 241 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-10500] due to args.save_total_limit
|
| 242 |
+
{'loss': 0.0463, 'learning_rate': 4.761904761904762e-06, 'epoch': 26.19}
|
| 243 |
+
***** Running Evaluation *****
|
| 244 |
+
Num examples = 420
|
| 245 |
+
Batch size = 8
|
| 246 |
+
{'eval_loss': 0.48534154891967773, 'eval_mse': 0.48534154891967773, 'eval_rmse': 0.696664571762085, 'eval_mae': 0.5263835191726685, 'eval_runtime': 1.1385, 'eval_samples_per_second': 368.9, 'eval_steps_per_second': 46.552, 'epoch': 27.0}
|
| 247 |
+
Saving model checkpoint to our_lipo_model/checkpoint-11340
|
| 248 |
+
Configuration saved in our_lipo_model/checkpoint-11340/config.json
|
| 249 |
+
Model weights saved in our_lipo_model/checkpoint-11340/pytorch_model.bin
|
| 250 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-10920] due to args.save_total_limit
|
| 251 |
+
{'loss': 0.0451, 'learning_rate': 4.523809523809524e-06, 'epoch': 27.38}
|
| 252 |
+
***** Running Evaluation *****
|
| 253 |
+
Num examples = 420
|
| 254 |
+
Batch size = 8
|
| 255 |
+
{'eval_loss': 0.4952319264411926, 'eval_mse': 0.4952319264411926, 'eval_rmse': 0.7037271857261658, 'eval_mae': 0.5382465720176697, 'eval_runtime': 1.1142, 'eval_samples_per_second': 376.951, 'eval_steps_per_second': 47.568, 'epoch': 28.0}
|
| 256 |
+
Saving model checkpoint to our_lipo_model/checkpoint-11760
|
| 257 |
+
Configuration saved in our_lipo_model/checkpoint-11760/config.json
|
| 258 |
+
Model weights saved in our_lipo_model/checkpoint-11760/pytorch_model.bin
|
| 259 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-11340] due to args.save_total_limit
|
| 260 |
+
{'loss': 0.0428, 'learning_rate': 4.2857142857142855e-06, 'epoch': 28.57}
|
| 261 |
+
***** Running Evaluation *****
|
| 262 |
+
Num examples = 420
|
| 263 |
+
Batch size = 8
|
| 264 |
+
{'eval_loss': 0.48455557227134705, 'eval_mse': 0.48455557227134705, 'eval_rmse': 0.6961002349853516, 'eval_mae': 0.529035210609436, 'eval_runtime': 1.1847, 'eval_samples_per_second': 354.512, 'eval_steps_per_second': 44.736, 'epoch': 29.0}
|
| 265 |
+
Saving model checkpoint to our_lipo_model/checkpoint-12180
|
| 266 |
+
Configuration saved in our_lipo_model/checkpoint-12180/config.json
|
| 267 |
+
Model weights saved in our_lipo_model/checkpoint-12180/pytorch_model.bin
|
| 268 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-11760] due to args.save_total_limit
|
| 269 |
+
{'loss': 0.0417, 'learning_rate': 4.047619047619048e-06, 'epoch': 29.76}
|
| 270 |
+
***** Running Evaluation *****
|
| 271 |
+
Num examples = 420
|
| 272 |
+
Batch size = 8
|
| 273 |
+
{'eval_loss': 0.4880525767803192, 'eval_mse': 0.4880525767803192, 'eval_rmse': 0.6986076235771179, 'eval_mae': 0.5353544354438782, 'eval_runtime': 1.2654, 'eval_samples_per_second': 331.922, 'eval_steps_per_second': 41.885, 'epoch': 30.0}
|
| 274 |
+
Saving model checkpoint to our_lipo_model/checkpoint-12600
|
| 275 |
+
Configuration saved in our_lipo_model/checkpoint-12600/config.json
|
| 276 |
+
Model weights saved in our_lipo_model/checkpoint-12600/pytorch_model.bin
|
| 277 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-12180] due to args.save_total_limit
|
| 278 |
+
{'loss': 0.0404, 'learning_rate': 3.80952380952381e-06, 'epoch': 30.95}
|
| 279 |
+
***** Running Evaluation *****
|
| 280 |
+
Num examples = 420
|
| 281 |
+
Batch size = 8
|
| 282 |
+
{'eval_loss': 0.48999953269958496, 'eval_mse': 0.4899995028972626, 'eval_rmse': 0.6999996304512024, 'eval_mae': 0.5326849222183228, 'eval_runtime': 1.2442, 'eval_samples_per_second': 337.554, 'eval_steps_per_second': 42.596, 'epoch': 31.0}
|
| 283 |
+
Saving model checkpoint to our_lipo_model/checkpoint-13020
|
| 284 |
+
Configuration saved in our_lipo_model/checkpoint-13020/config.json
|
| 285 |
+
Model weights saved in our_lipo_model/checkpoint-13020/pytorch_model.bin
|
| 286 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-12600] due to args.save_total_limit
|
| 287 |
+
***** Running Evaluation *****
|
| 288 |
+
Num examples = 420
|
| 289 |
+
Batch size = 8
|
| 290 |
+
{'eval_loss': 0.5017576813697815, 'eval_mse': 0.5017576813697815, 'eval_rmse': 0.7083485722541809, 'eval_mae': 0.5423673987388611, 'eval_runtime': 1.1196, 'eval_samples_per_second': 375.135, 'eval_steps_per_second': 47.339, 'epoch': 32.0}
|
| 291 |
+
Saving model checkpoint to our_lipo_model/checkpoint-13440
|
| 292 |
+
Configuration saved in our_lipo_model/checkpoint-13440/config.json
|
| 293 |
+
Model weights saved in our_lipo_model/checkpoint-13440/pytorch_model.bin
|
| 294 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-13020] due to args.save_total_limit
|
| 295 |
+
{'loss': 0.0391, 'learning_rate': 3.5714285714285718e-06, 'epoch': 32.14}
|
| 296 |
+
***** Running Evaluation *****
|
| 297 |
+
Num examples = 420
|
| 298 |
+
Batch size = 8
|
| 299 |
+
{'eval_loss': 0.48715752363204956, 'eval_mse': 0.48715752363204956, 'eval_rmse': 0.6979666948318481, 'eval_mae': 0.5341249108314514, 'eval_runtime': 1.1228, 'eval_samples_per_second': 374.062, 'eval_steps_per_second': 47.203, 'epoch': 33.0}
|
| 300 |
+
Saving model checkpoint to our_lipo_model/checkpoint-13860
|
| 301 |
+
Configuration saved in our_lipo_model/checkpoint-13860/config.json
|
| 302 |
+
Model weights saved in our_lipo_model/checkpoint-13860/pytorch_model.bin
|
| 303 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-13440] due to args.save_total_limit
|
| 304 |
+
{'loss': 0.0373, 'learning_rate': 3.3333333333333333e-06, 'epoch': 33.33}
|
| 305 |
+
***** Running Evaluation *****
|
| 306 |
+
Num examples = 420
|
| 307 |
+
Batch size = 8
|
| 308 |
+
{'eval_loss': 0.479116827249527, 'eval_mse': 0.479116827249527, 'eval_rmse': 0.6921826601028442, 'eval_mae': 0.5321008563041687, 'eval_runtime': 1.206, 'eval_samples_per_second': 348.254, 'eval_steps_per_second': 43.946, 'epoch': 34.0}
|
| 309 |
+
Saving model checkpoint to our_lipo_model/checkpoint-14280
|
| 310 |
+
Configuration saved in our_lipo_model/checkpoint-14280/config.json
|
| 311 |
+
Model weights saved in our_lipo_model/checkpoint-14280/pytorch_model.bin
|
| 312 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-13860] due to args.save_total_limit
|
| 313 |
+
{'loss': 0.0359, 'learning_rate': 3.0952380952380957e-06, 'epoch': 34.52}
|
| 314 |
+
***** Running Evaluation *****
|
| 315 |
+
Num examples = 420
|
| 316 |
+
Batch size = 8
|
| 317 |
+
{'eval_loss': 0.48590707778930664, 'eval_mse': 0.48590704798698425, 'eval_rmse': 0.6970703601837158, 'eval_mae': 0.5346122980117798, 'eval_runtime': 0.8892, 'eval_samples_per_second': 472.339, 'eval_steps_per_second': 59.605, 'epoch': 35.0}
|
| 318 |
+
Saving model checkpoint to our_lipo_model/checkpoint-14700
|
| 319 |
+
Configuration saved in our_lipo_model/checkpoint-14700/config.json
|
| 320 |
+
Model weights saved in our_lipo_model/checkpoint-14700/pytorch_model.bin
|
| 321 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-14280] due to args.save_total_limit
|
| 322 |
+
{'loss': 0.0334, 'learning_rate': 2.8571428571428573e-06, 'epoch': 35.71}
|
| 323 |
+
***** Running Evaluation *****
|
| 324 |
+
Num examples = 420
|
| 325 |
+
Batch size = 8
|
| 326 |
+
{'eval_loss': 0.4766678810119629, 'eval_mse': 0.4766678810119629, 'eval_rmse': 0.690411388874054, 'eval_mae': 0.5263535380363464, 'eval_runtime': 1.286, 'eval_samples_per_second': 326.603, 'eval_steps_per_second': 41.214, 'epoch': 36.0}
|
| 327 |
+
Saving model checkpoint to our_lipo_model/checkpoint-15120
|
| 328 |
+
Configuration saved in our_lipo_model/checkpoint-15120/config.json
|
| 329 |
+
Model weights saved in our_lipo_model/checkpoint-15120/pytorch_model.bin
|
| 330 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-14700] due to args.save_total_limit
|
| 331 |
+
{'loss': 0.0341, 'learning_rate': 2.6190476190476192e-06, 'epoch': 36.9}
|
| 332 |
+
***** Running Evaluation *****
|
| 333 |
+
Num examples = 420
|
| 334 |
+
Batch size = 8
|
| 335 |
+
{'eval_loss': 0.4740683436393738, 'eval_mse': 0.4740683138370514, 'eval_rmse': 0.6885262131690979, 'eval_mae': 0.5217899680137634, 'eval_runtime': 1.1893, 'eval_samples_per_second': 353.162, 'eval_steps_per_second': 44.566, 'epoch': 37.0}
|
| 336 |
+
Saving model checkpoint to our_lipo_model/checkpoint-15540
|
| 337 |
+
Configuration saved in our_lipo_model/checkpoint-15540/config.json
|
| 338 |
+
Model weights saved in our_lipo_model/checkpoint-15540/pytorch_model.bin
|
| 339 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-15120] due to args.save_total_limit
|
| 340 |
+
***** Running Evaluation *****
|
| 341 |
+
Num examples = 420
|
| 342 |
+
Batch size = 8
|
| 343 |
+
{'eval_loss': 0.478584349155426, 'eval_mse': 0.478584349155426, 'eval_rmse': 0.6917979121208191, 'eval_mae': 0.527285635471344, 'eval_runtime': 1.1477, 'eval_samples_per_second': 365.939, 'eval_steps_per_second': 46.178, 'epoch': 38.0}
|
| 344 |
+
Saving model checkpoint to our_lipo_model/checkpoint-15960
|
| 345 |
+
Configuration saved in our_lipo_model/checkpoint-15960/config.json
|
| 346 |
+
Model weights saved in our_lipo_model/checkpoint-15960/pytorch_model.bin
|
| 347 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-15540] due to args.save_total_limit
|
| 348 |
+
{'loss': 0.0325, 'learning_rate': 2.380952380952381e-06, 'epoch': 38.1}
|
| 349 |
+
***** Running Evaluation *****
|
| 350 |
+
Num examples = 420
|
| 351 |
+
Batch size = 8
|
| 352 |
+
{'eval_loss': 0.46834418177604675, 'eval_mse': 0.46834418177604675, 'eval_rmse': 0.6843567490577698, 'eval_mae': 0.5196450352668762, 'eval_runtime': 1.1282, 'eval_samples_per_second': 372.276, 'eval_steps_per_second': 46.978, 'epoch': 39.0}
|
| 353 |
+
Saving model checkpoint to our_lipo_model/checkpoint-16380
|
| 354 |
+
Configuration saved in our_lipo_model/checkpoint-16380/config.json
|
| 355 |
+
Model weights saved in our_lipo_model/checkpoint-16380/pytorch_model.bin
|
| 356 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-15960] due to args.save_total_limit
|
| 357 |
+
{'loss': 0.0331, 'learning_rate': 2.1428571428571427e-06, 'epoch': 39.29}
|
| 358 |
+
***** Running Evaluation *****
|
| 359 |
+
Num examples = 420
|
| 360 |
+
Batch size = 8
|
| 361 |
+
{'eval_loss': 0.46904683113098145, 'eval_mse': 0.46904683113098145, 'eval_rmse': 0.6848699450492859, 'eval_mae': 0.522687554359436, 'eval_runtime': 1.1578, 'eval_samples_per_second': 362.764, 'eval_steps_per_second': 45.777, 'epoch': 40.0}
|
| 362 |
+
Saving model checkpoint to our_lipo_model/checkpoint-16800
|
| 363 |
+
Configuration saved in our_lipo_model/checkpoint-16800/config.json
|
| 364 |
+
Model weights saved in our_lipo_model/checkpoint-16800/pytorch_model.bin
|
| 365 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-16380] due to args.save_total_limit
|
| 366 |
+
{'loss': 0.0315, 'learning_rate': 1.904761904761905e-06, 'epoch': 40.48}
|
| 367 |
+
***** Running Evaluation *****
|
| 368 |
+
Num examples = 420
|
| 369 |
+
Batch size = 8
|
| 370 |
+
{'eval_loss': 0.46947211027145386, 'eval_mse': 0.46947211027145386, 'eval_rmse': 0.6851803660392761, 'eval_mae': 0.5197708010673523, 'eval_runtime': 1.1711, 'eval_samples_per_second': 358.64, 'eval_steps_per_second': 45.257, 'epoch': 41.0}
|
| 371 |
+
Saving model checkpoint to our_lipo_model/checkpoint-17220
|
| 372 |
+
Configuration saved in our_lipo_model/checkpoint-17220/config.json
|
| 373 |
+
Model weights saved in our_lipo_model/checkpoint-17220/pytorch_model.bin
|
| 374 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-16800] due to args.save_total_limit
|
| 375 |
+
{'loss': 0.0299, 'learning_rate': 1.6666666666666667e-06, 'epoch': 41.67}
|
| 376 |
+
***** Running Evaluation *****
|
| 377 |
+
Num examples = 420
|
| 378 |
+
Batch size = 8
|
| 379 |
+
{'eval_loss': 0.46514230966567993, 'eval_mse': 0.46514227986335754, 'eval_rmse': 0.6820133924484253, 'eval_mae': 0.518059253692627, 'eval_runtime': 1.1482, 'eval_samples_per_second': 365.797, 'eval_steps_per_second': 46.16, 'epoch': 42.0}
|
| 380 |
+
Saving model checkpoint to our_lipo_model/checkpoint-17640
|
| 381 |
+
Configuration saved in our_lipo_model/checkpoint-17640/config.json
|
| 382 |
+
Model weights saved in our_lipo_model/checkpoint-17640/pytorch_model.bin
|
| 383 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-17220] due to args.save_total_limit
|
| 384 |
+
{'loss': 0.0314, 'learning_rate': 1.4285714285714286e-06, 'epoch': 42.86}
|
| 385 |
+
***** Running Evaluation *****
|
| 386 |
+
Num examples = 420
|
| 387 |
+
Batch size = 8
|
| 388 |
+
{'eval_loss': 0.4640100300312042, 'eval_mse': 0.46400997042655945, 'eval_rmse': 0.6811828017234802, 'eval_mae': 0.51801997423172, 'eval_runtime': 1.1908, 'eval_samples_per_second': 352.696, 'eval_steps_per_second': 44.507, 'epoch': 43.0}
|
| 389 |
+
Saving model checkpoint to our_lipo_model/checkpoint-18060
|
| 390 |
+
Configuration saved in our_lipo_model/checkpoint-18060/config.json
|
| 391 |
+
Model weights saved in our_lipo_model/checkpoint-18060/pytorch_model.bin
|
| 392 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-17640] due to args.save_total_limit
|
| 393 |
+
***** Running Evaluation *****
|
| 394 |
+
Num examples = 420
|
| 395 |
+
Batch size = 8
|
| 396 |
+
{'eval_loss': 0.4704785943031311, 'eval_mse': 0.4704785943031311, 'eval_rmse': 0.6859143972396851, 'eval_mae': 0.5230998992919922, 'eval_runtime': 1.2463, 'eval_samples_per_second': 337.011, 'eval_steps_per_second': 42.528, 'epoch': 44.0}
|
| 397 |
+
Saving model checkpoint to our_lipo_model/checkpoint-18480
|
| 398 |
+
Configuration saved in our_lipo_model/checkpoint-18480/config.json
|
| 399 |
+
Model weights saved in our_lipo_model/checkpoint-18480/pytorch_model.bin
|
| 400 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-18060] due to args.save_total_limit
|
| 401 |
+
{'loss': 0.0283, 'learning_rate': 1.1904761904761906e-06, 'epoch': 44.05}
|
| 402 |
+
***** Running Evaluation *****
|
| 403 |
+
Num examples = 420
|
| 404 |
+
Batch size = 8
|
| 405 |
+
{'eval_loss': 0.4678580164909363, 'eval_mse': 0.46785807609558105, 'eval_rmse': 0.6840015053749084, 'eval_mae': 0.521861732006073, 'eval_runtime': 1.2433, 'eval_samples_per_second': 337.812, 'eval_steps_per_second': 42.629, 'epoch': 45.0}
|
| 406 |
+
Saving model checkpoint to our_lipo_model/checkpoint-18900
|
| 407 |
+
Configuration saved in our_lipo_model/checkpoint-18900/config.json
|
| 408 |
+
Model weights saved in our_lipo_model/checkpoint-18900/pytorch_model.bin
|
| 409 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-18480] due to args.save_total_limit
|
| 410 |
+
{'loss': 0.0284, 'learning_rate': 9.523809523809525e-07, 'epoch': 45.24}
|
| 411 |
+
***** Running Evaluation *****
|
| 412 |
+
Num examples = 420
|
| 413 |
+
Batch size = 8
|
| 414 |
+
{'eval_loss': 0.4686986207962036, 'eval_mse': 0.4686986207962036, 'eval_rmse': 0.6846156716346741, 'eval_mae': 0.5229542851448059, 'eval_runtime': 1.1892, 'eval_samples_per_second': 353.193, 'eval_steps_per_second': 44.57, 'epoch': 46.0}
|
| 415 |
+
Saving model checkpoint to our_lipo_model/checkpoint-19320
|
| 416 |
+
Configuration saved in our_lipo_model/checkpoint-19320/config.json
|
| 417 |
+
Model weights saved in our_lipo_model/checkpoint-19320/pytorch_model.bin
|
| 418 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-18900] due to args.save_total_limit
|
| 419 |
+
{'loss': 0.0273, 'learning_rate': 7.142857142857143e-07, 'epoch': 46.43}
|
| 420 |
+
***** Running Evaluation *****
|
| 421 |
+
Num examples = 420
|
| 422 |
+
Batch size = 8
|
| 423 |
+
{'eval_loss': 0.46382173895835876, 'eval_mse': 0.4638217091560364, 'eval_rmse': 0.6810445785522461, 'eval_mae': 0.5197833776473999, 'eval_runtime': 1.2872, 'eval_samples_per_second': 326.279, 'eval_steps_per_second': 41.173, 'epoch': 47.0}
|
| 424 |
+
Saving model checkpoint to our_lipo_model/checkpoint-19740
|
| 425 |
+
Configuration saved in our_lipo_model/checkpoint-19740/config.json
|
| 426 |
+
Model weights saved in our_lipo_model/checkpoint-19740/pytorch_model.bin
|
| 427 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-19320] due to args.save_total_limit
|
| 428 |
+
{'loss': 0.0283, 'learning_rate': 4.7619047619047623e-07, 'epoch': 47.62}
|
| 429 |
+
***** Running Evaluation *****
|
| 430 |
+
Num examples = 420
|
| 431 |
+
Batch size = 8
|
| 432 |
+
{'eval_loss': 0.4631454348564148, 'eval_mse': 0.4631454348564148, 'eval_rmse': 0.6805478930473328, 'eval_mae': 0.5184262990951538, 'eval_runtime': 1.1721, 'eval_samples_per_second': 358.345, 'eval_steps_per_second': 45.22, 'epoch': 48.0}
|
| 433 |
+
Saving model checkpoint to our_lipo_model/checkpoint-20160
|
| 434 |
+
Configuration saved in our_lipo_model/checkpoint-20160/config.json
|
| 435 |
+
Model weights saved in our_lipo_model/checkpoint-20160/pytorch_model.bin
|
| 436 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-19740] due to args.save_total_limit
|
| 437 |
+
{'loss': 0.0268, 'learning_rate': 2.3809523809523811e-07, 'epoch': 48.81}
|
| 438 |
+
***** Running Evaluation *****
|
| 439 |
+
Num examples = 420
|
| 440 |
+
Batch size = 8
|
| 441 |
+
{'eval_loss': 0.4649342894554138, 'eval_mse': 0.4649342894554138, 'eval_rmse': 0.6818609237670898, 'eval_mae': 0.5196540355682373, 'eval_runtime': 1.1402, 'eval_samples_per_second': 368.356, 'eval_steps_per_second': 46.483, 'epoch': 49.0}
|
| 442 |
+
Saving model checkpoint to our_lipo_model/checkpoint-20580
|
| 443 |
+
Configuration saved in our_lipo_model/checkpoint-20580/config.json
|
| 444 |
+
Model weights saved in our_lipo_model/checkpoint-20580/pytorch_model.bin
|
| 445 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-20160] due to args.save_total_limit
|
| 446 |
+
{'loss': 0.0269, 'learning_rate': 0.0, 'epoch': 50.0}
|
| 447 |
+
***** Running Evaluation *****
|
| 448 |
+
Num examples = 420
|
| 449 |
+
Batch size = 8
|
| 450 |
+
{'eval_loss': 0.46444272994995117, 'eval_mse': 0.46444275975227356, 'eval_rmse': 0.6815003752708435, 'eval_mae': 0.5188572406768799, 'eval_runtime': 1.0966, 'eval_samples_per_second': 382.987, 'eval_steps_per_second': 48.329, 'epoch': 50.0}
|
| 451 |
+
Saving model checkpoint to our_lipo_model/checkpoint-21000
|
| 452 |
+
Configuration saved in our_lipo_model/checkpoint-21000/config.json
|
| 453 |
+
Model weights saved in our_lipo_model/checkpoint-21000/pytorch_model.bin
|
| 454 |
+
Deleting older checkpoint [our_lipo_model/checkpoint-20580] due to args.save_total_limit
|
| 455 |
+
|
| 456 |
+
|
| 457 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
| 458 |
+
|
| 459 |
+
|
| 460 |
+
{'train_runtime': 2521.2916, 'train_samples_per_second': 66.633, 'train_steps_per_second': 8.329, 'train_loss': 0.10468049140203567, 'epoch': 50.0}
|
| 461 |
+
Metrics
|
| 462 |
+
TrainOutput(global_step=21000, training_loss=0.10468049140203567, metrics={'train_runtime': 2521.2916, 'train_samples_per_second': 66.633, 'train_steps_per_second': 8.329, 'train_loss': 0.10468049140203567, 'epoch': 50.0})
|
| 463 |
+
Saving model checkpoint to our_lipo_model
|
| 464 |
+
Configuration saved in our_lipo_model/config.json
|
| 465 |
+
Model weights saved in our_lipo_model/pytorch_model.bin
|
| 466 |
+
***** Running Prediction *****
|
| 467 |
+
Num examples = 420
|
| 468 |
+
Batch size = 8
|
| 469 |
+
|
| 470 |
+
Mean Squared Error (MSE): 0.5401966615179934
|
| 471 |
+
Root Mean Square Error (RMSE): 0.7349807218682632
|
| 472 |
+
Mean Absolute Error (MAE): 0.5634666012316232
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3b51560e9cff09ca9b47178b881764ff5e594c97346769443ee5b9568d55d1
|
| 3 |
+
size 349077673
|
runs/Apr09_13-58-13_lotan/1649512701.6283627/events.out.tfevents.1649512701.lotan.2908185.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bff04cb85afd30b6243be075f90e7f2b1826e160a91e1489a743a0615eb4ad0
|
| 3 |
+
size 4715
|
runs/Apr09_13-58-13_lotan/events.out.tfevents.1649512701.lotan.2908185.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ae8fdcca64bfe3c0adfd963a83005a26d36062ae612582762cd6b96a8402680
|
| 3 |
+
size 31112
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28de34ee8013d54b9b537082795de541af9b7e6264c92b19a1cb5e5e3df7cfdb
|
| 3 |
+
size 2927
|