Upload with huggingface_hub
Browse files- checkpoint-4450/config.json +33 -0
- checkpoint-4450/optimizer.pt +3 -0
- checkpoint-4450/pytorch_model.bin +3 -0
- checkpoint-4450/rng_state.pth +3 -0
- checkpoint-4450/scheduler.pt +3 -0
- checkpoint-4450/trainer_state.json +614 -0
- checkpoint-4450/training_args.bin +3 -0
- config.json +33 -0
- esol.out +438 -0
- pytorch_model.bin +3 -0
- runs/Apr09_13-58-06_lotan/1649512692.4007227/events.out.tfevents.1649512692.lotan.2908091.1 +3 -0
- runs/Apr09_13-58-06_lotan/events.out.tfevents.1649512692.lotan.2908091.0 +3 -0
- training_args.bin +3 -0
checkpoint-4450/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-4450/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1130a540f3636f511b1e5efb15636e4160ca542f13b4df33179e67fd454f6fc9
|
| 3 |
+
size 693374749
|
checkpoint-4450/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9cc2ad8d7639cc750cd8a674d0acf96eda2c3b278a93a3a842e9c199ae8c513
|
| 3 |
+
size 349077673
|
checkpoint-4450/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e38d4cdd4f0ff81c2449c3b4a0c334a65fe07517baf28a190b622f57ea36117
|
| 3 |
+
size 14503
|
checkpoint-4450/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9c1f68366b44491e9f3148fb4d844bf77877b0b978d6146bad2f115e396b85f
|
| 3 |
+
size 623
|
checkpoint-4450/trainer_state.json
ADDED
|
@@ -0,0 +1,614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 4450,
|
| 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": 1.7501213550567627,
|
| 13 |
+
"eval_mae": 1.0687230825424194,
|
| 14 |
+
"eval_mse": 1.750120997428894,
|
| 15 |
+
"eval_rmse": 1.3229213953018188,
|
| 16 |
+
"eval_runtime": 0.213,
|
| 17 |
+
"eval_samples_per_second": 323.879,
|
| 18 |
+
"eval_steps_per_second": 42.245,
|
| 19 |
+
"step": 89
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 2.0,
|
| 23 |
+
"eval_loss": 0.9408809542655945,
|
| 24 |
+
"eval_mae": 0.7522120475769043,
|
| 25 |
+
"eval_mse": 0.9408809542655945,
|
| 26 |
+
"eval_rmse": 0.9699901938438416,
|
| 27 |
+
"eval_runtime": 0.4675,
|
| 28 |
+
"eval_samples_per_second": 147.6,
|
| 29 |
+
"eval_steps_per_second": 19.252,
|
| 30 |
+
"step": 178
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.0,
|
| 34 |
+
"eval_loss": 0.7912163138389587,
|
| 35 |
+
"eval_mae": 0.7013395428657532,
|
| 36 |
+
"eval_mse": 0.7912163734436035,
|
| 37 |
+
"eval_rmse": 0.8895034193992615,
|
| 38 |
+
"eval_runtime": 0.4829,
|
| 39 |
+
"eval_samples_per_second": 142.893,
|
| 40 |
+
"eval_steps_per_second": 18.638,
|
| 41 |
+
"step": 267
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 4.0,
|
| 45 |
+
"eval_loss": 0.7405096292495728,
|
| 46 |
+
"eval_mae": 0.6587470769882202,
|
| 47 |
+
"eval_mse": 0.7405097484588623,
|
| 48 |
+
"eval_rmse": 0.8605287671089172,
|
| 49 |
+
"eval_runtime": 0.4491,
|
| 50 |
+
"eval_samples_per_second": 153.654,
|
| 51 |
+
"eval_steps_per_second": 20.042,
|
| 52 |
+
"step": 356
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 5.0,
|
| 56 |
+
"eval_loss": 0.6923832297325134,
|
| 57 |
+
"eval_mae": 0.6610296964645386,
|
| 58 |
+
"eval_mse": 0.6923832893371582,
|
| 59 |
+
"eval_rmse": 0.832095742225647,
|
| 60 |
+
"eval_runtime": 0.4191,
|
| 61 |
+
"eval_samples_per_second": 164.64,
|
| 62 |
+
"eval_steps_per_second": 21.475,
|
| 63 |
+
"step": 445
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.62,
|
| 67 |
+
"learning_rate": 8.876404494382023e-06,
|
| 68 |
+
"loss": 0.9104,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 6.0,
|
| 73 |
+
"eval_loss": 0.6709772944450378,
|
| 74 |
+
"eval_mae": 0.6442688703536987,
|
| 75 |
+
"eval_mse": 0.6709771752357483,
|
| 76 |
+
"eval_rmse": 0.8191319704055786,
|
| 77 |
+
"eval_runtime": 0.4743,
|
| 78 |
+
"eval_samples_per_second": 145.467,
|
| 79 |
+
"eval_steps_per_second": 18.974,
|
| 80 |
+
"step": 534
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 7.0,
|
| 84 |
+
"eval_loss": 0.5820761322975159,
|
| 85 |
+
"eval_mae": 0.6152850389480591,
|
| 86 |
+
"eval_mse": 0.5820761919021606,
|
| 87 |
+
"eval_rmse": 0.7629391551017761,
|
| 88 |
+
"eval_runtime": 0.364,
|
| 89 |
+
"eval_samples_per_second": 189.553,
|
| 90 |
+
"eval_steps_per_second": 24.724,
|
| 91 |
+
"step": 623
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 8.0,
|
| 95 |
+
"eval_loss": 0.49572908878326416,
|
| 96 |
+
"eval_mae": 0.5509689450263977,
|
| 97 |
+
"eval_mse": 0.49572914838790894,
|
| 98 |
+
"eval_rmse": 0.70408034324646,
|
| 99 |
+
"eval_runtime": 0.4466,
|
| 100 |
+
"eval_samples_per_second": 154.492,
|
| 101 |
+
"eval_steps_per_second": 20.151,
|
| 102 |
+
"step": 712
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 9.0,
|
| 106 |
+
"eval_loss": 0.5924321413040161,
|
| 107 |
+
"eval_mae": 0.6066040396690369,
|
| 108 |
+
"eval_mse": 0.5924323201179504,
|
| 109 |
+
"eval_rmse": 0.7696962356567383,
|
| 110 |
+
"eval_runtime": 0.4645,
|
| 111 |
+
"eval_samples_per_second": 148.549,
|
| 112 |
+
"eval_steps_per_second": 19.376,
|
| 113 |
+
"step": 801
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 10.0,
|
| 117 |
+
"eval_loss": 0.4954969882965088,
|
| 118 |
+
"eval_mae": 0.5473751425743103,
|
| 119 |
+
"eval_mse": 0.4954971671104431,
|
| 120 |
+
"eval_rmse": 0.7039155960083008,
|
| 121 |
+
"eval_runtime": 0.3698,
|
| 122 |
+
"eval_samples_per_second": 186.61,
|
| 123 |
+
"eval_steps_per_second": 24.34,
|
| 124 |
+
"step": 890
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 11.0,
|
| 128 |
+
"eval_loss": 0.5200049877166748,
|
| 129 |
+
"eval_mae": 0.5685440897941589,
|
| 130 |
+
"eval_mse": 0.52000492811203,
|
| 131 |
+
"eval_rmse": 0.7211136817932129,
|
| 132 |
+
"eval_runtime": 0.4266,
|
| 133 |
+
"eval_samples_per_second": 161.746,
|
| 134 |
+
"eval_steps_per_second": 21.097,
|
| 135 |
+
"step": 979
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 11.24,
|
| 139 |
+
"learning_rate": 7.752808988764046e-06,
|
| 140 |
+
"loss": 0.128,
|
| 141 |
+
"step": 1000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 12.0,
|
| 145 |
+
"eval_loss": 0.43686971068382263,
|
| 146 |
+
"eval_mae": 0.5061944723129272,
|
| 147 |
+
"eval_mse": 0.436869740486145,
|
| 148 |
+
"eval_rmse": 0.6609612107276917,
|
| 149 |
+
"eval_runtime": 0.4821,
|
| 150 |
+
"eval_samples_per_second": 143.124,
|
| 151 |
+
"eval_steps_per_second": 18.668,
|
| 152 |
+
"step": 1068
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 13.0,
|
| 156 |
+
"eval_loss": 0.41416943073272705,
|
| 157 |
+
"eval_mae": 0.46771711111068726,
|
| 158 |
+
"eval_mse": 0.41416940093040466,
|
| 159 |
+
"eval_rmse": 0.6435599327087402,
|
| 160 |
+
"eval_runtime": 0.4624,
|
| 161 |
+
"eval_samples_per_second": 149.23,
|
| 162 |
+
"eval_steps_per_second": 19.465,
|
| 163 |
+
"step": 1157
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 14.0,
|
| 167 |
+
"eval_loss": 0.40698668360710144,
|
| 168 |
+
"eval_mae": 0.45521026849746704,
|
| 169 |
+
"eval_mse": 0.4069867730140686,
|
| 170 |
+
"eval_rmse": 0.6379551291465759,
|
| 171 |
+
"eval_runtime": 0.4757,
|
| 172 |
+
"eval_samples_per_second": 145.044,
|
| 173 |
+
"eval_steps_per_second": 18.919,
|
| 174 |
+
"step": 1246
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 15.0,
|
| 178 |
+
"eval_loss": 0.49930572509765625,
|
| 179 |
+
"eval_mae": 0.5383840799331665,
|
| 180 |
+
"eval_mse": 0.4993056654930115,
|
| 181 |
+
"eval_rmse": 0.7066156268119812,
|
| 182 |
+
"eval_runtime": 0.4656,
|
| 183 |
+
"eval_samples_per_second": 148.181,
|
| 184 |
+
"eval_steps_per_second": 19.328,
|
| 185 |
+
"step": 1335
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 16.0,
|
| 189 |
+
"eval_loss": 0.5578888654708862,
|
| 190 |
+
"eval_mae": 0.585189163684845,
|
| 191 |
+
"eval_mse": 0.5578888058662415,
|
| 192 |
+
"eval_rmse": 0.746919572353363,
|
| 193 |
+
"eval_runtime": 0.4755,
|
| 194 |
+
"eval_samples_per_second": 145.098,
|
| 195 |
+
"eval_steps_per_second": 18.926,
|
| 196 |
+
"step": 1424
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 16.85,
|
| 200 |
+
"learning_rate": 6.629213483146067e-06,
|
| 201 |
+
"loss": 0.0895,
|
| 202 |
+
"step": 1500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 17.0,
|
| 206 |
+
"eval_loss": 0.5015009045600891,
|
| 207 |
+
"eval_mae": 0.561897337436676,
|
| 208 |
+
"eval_mse": 0.5015009641647339,
|
| 209 |
+
"eval_rmse": 0.708167314529419,
|
| 210 |
+
"eval_runtime": 0.3883,
|
| 211 |
+
"eval_samples_per_second": 177.714,
|
| 212 |
+
"eval_steps_per_second": 23.18,
|
| 213 |
+
"step": 1513
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 18.0,
|
| 217 |
+
"eval_loss": 0.4590393602848053,
|
| 218 |
+
"eval_mae": 0.5263462066650391,
|
| 219 |
+
"eval_mse": 0.45903947949409485,
|
| 220 |
+
"eval_rmse": 0.6775245070457458,
|
| 221 |
+
"eval_runtime": 0.4835,
|
| 222 |
+
"eval_samples_per_second": 142.705,
|
| 223 |
+
"eval_steps_per_second": 18.614,
|
| 224 |
+
"step": 1602
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 19.0,
|
| 228 |
+
"eval_loss": 0.4880666434764862,
|
| 229 |
+
"eval_mae": 0.5377508997917175,
|
| 230 |
+
"eval_mse": 0.4880666732788086,
|
| 231 |
+
"eval_rmse": 0.698617696762085,
|
| 232 |
+
"eval_runtime": 0.4715,
|
| 233 |
+
"eval_samples_per_second": 146.34,
|
| 234 |
+
"eval_steps_per_second": 19.088,
|
| 235 |
+
"step": 1691
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 20.0,
|
| 239 |
+
"eval_loss": 0.3925124704837799,
|
| 240 |
+
"eval_mae": 0.46625784039497375,
|
| 241 |
+
"eval_mse": 0.3925124406814575,
|
| 242 |
+
"eval_rmse": 0.6265081167221069,
|
| 243 |
+
"eval_runtime": 0.3158,
|
| 244 |
+
"eval_samples_per_second": 218.521,
|
| 245 |
+
"eval_steps_per_second": 28.503,
|
| 246 |
+
"step": 1780
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 21.0,
|
| 250 |
+
"eval_loss": 0.4392476975917816,
|
| 251 |
+
"eval_mae": 0.5062677264213562,
|
| 252 |
+
"eval_mse": 0.4392476975917816,
|
| 253 |
+
"eval_rmse": 0.6627576351165771,
|
| 254 |
+
"eval_runtime": 0.4321,
|
| 255 |
+
"eval_samples_per_second": 159.696,
|
| 256 |
+
"eval_steps_per_second": 20.83,
|
| 257 |
+
"step": 1869
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 22.0,
|
| 261 |
+
"eval_loss": 0.42705094814300537,
|
| 262 |
+
"eval_mae": 0.48886218667030334,
|
| 263 |
+
"eval_mse": 0.42705097794532776,
|
| 264 |
+
"eval_rmse": 0.6534913778305054,
|
| 265 |
+
"eval_runtime": 0.3907,
|
| 266 |
+
"eval_samples_per_second": 176.595,
|
| 267 |
+
"eval_steps_per_second": 23.034,
|
| 268 |
+
"step": 1958
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 22.47,
|
| 272 |
+
"learning_rate": 5.50561797752809e-06,
|
| 273 |
+
"loss": 0.0694,
|
| 274 |
+
"step": 2000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 23.0,
|
| 278 |
+
"eval_loss": 0.40933796763420105,
|
| 279 |
+
"eval_mae": 0.4783601760864258,
|
| 280 |
+
"eval_mse": 0.4093380868434906,
|
| 281 |
+
"eval_rmse": 0.6397953629493713,
|
| 282 |
+
"eval_runtime": 0.3371,
|
| 283 |
+
"eval_samples_per_second": 204.706,
|
| 284 |
+
"eval_steps_per_second": 26.701,
|
| 285 |
+
"step": 2047
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 24.0,
|
| 289 |
+
"eval_loss": 0.42077454924583435,
|
| 290 |
+
"eval_mae": 0.49500545859336853,
|
| 291 |
+
"eval_mse": 0.42077454924583435,
|
| 292 |
+
"eval_rmse": 0.6486713886260986,
|
| 293 |
+
"eval_runtime": 0.4775,
|
| 294 |
+
"eval_samples_per_second": 144.493,
|
| 295 |
+
"eval_steps_per_second": 18.847,
|
| 296 |
+
"step": 2136
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 25.0,
|
| 300 |
+
"eval_loss": 0.40650996565818787,
|
| 301 |
+
"eval_mae": 0.4869938790798187,
|
| 302 |
+
"eval_mse": 0.4065099358558655,
|
| 303 |
+
"eval_rmse": 0.6375812888145447,
|
| 304 |
+
"eval_runtime": 0.4751,
|
| 305 |
+
"eval_samples_per_second": 145.227,
|
| 306 |
+
"eval_steps_per_second": 18.943,
|
| 307 |
+
"step": 2225
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 26.0,
|
| 311 |
+
"eval_loss": 0.4467940032482147,
|
| 312 |
+
"eval_mae": 0.5186977386474609,
|
| 313 |
+
"eval_mse": 0.44679397344589233,
|
| 314 |
+
"eval_rmse": 0.668426513671875,
|
| 315 |
+
"eval_runtime": 0.4523,
|
| 316 |
+
"eval_samples_per_second": 152.552,
|
| 317 |
+
"eval_steps_per_second": 19.898,
|
| 318 |
+
"step": 2314
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 27.0,
|
| 322 |
+
"eval_loss": 0.448551744222641,
|
| 323 |
+
"eval_mae": 0.5286442041397095,
|
| 324 |
+
"eval_mse": 0.4485517740249634,
|
| 325 |
+
"eval_rmse": 0.6697400808334351,
|
| 326 |
+
"eval_runtime": 0.3607,
|
| 327 |
+
"eval_samples_per_second": 191.288,
|
| 328 |
+
"eval_steps_per_second": 24.951,
|
| 329 |
+
"step": 2403
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 28.0,
|
| 333 |
+
"eval_loss": 0.4263148605823517,
|
| 334 |
+
"eval_mae": 0.5110523700714111,
|
| 335 |
+
"eval_mse": 0.4263148009777069,
|
| 336 |
+
"eval_rmse": 0.6529278755187988,
|
| 337 |
+
"eval_runtime": 0.4741,
|
| 338 |
+
"eval_samples_per_second": 145.544,
|
| 339 |
+
"eval_steps_per_second": 18.984,
|
| 340 |
+
"step": 2492
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 28.09,
|
| 344 |
+
"learning_rate": 4.382022471910113e-06,
|
| 345 |
+
"loss": 0.0575,
|
| 346 |
+
"step": 2500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 29.0,
|
| 350 |
+
"eval_loss": 0.4624464213848114,
|
| 351 |
+
"eval_mae": 0.5141972303390503,
|
| 352 |
+
"eval_mse": 0.462446391582489,
|
| 353 |
+
"eval_rmse": 0.6800341010093689,
|
| 354 |
+
"eval_runtime": 0.4737,
|
| 355 |
+
"eval_samples_per_second": 145.658,
|
| 356 |
+
"eval_steps_per_second": 18.999,
|
| 357 |
+
"step": 2581
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 30.0,
|
| 361 |
+
"eval_loss": 0.4065593481063843,
|
| 362 |
+
"eval_mae": 0.4846087396144867,
|
| 363 |
+
"eval_mse": 0.40655940771102905,
|
| 364 |
+
"eval_rmse": 0.6376200914382935,
|
| 365 |
+
"eval_runtime": 0.3326,
|
| 366 |
+
"eval_samples_per_second": 207.482,
|
| 367 |
+
"eval_steps_per_second": 27.063,
|
| 368 |
+
"step": 2670
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 31.0,
|
| 372 |
+
"eval_loss": 0.4373004138469696,
|
| 373 |
+
"eval_mae": 0.5060880780220032,
|
| 374 |
+
"eval_mse": 0.437300443649292,
|
| 375 |
+
"eval_rmse": 0.6612869501113892,
|
| 376 |
+
"eval_runtime": 0.4249,
|
| 377 |
+
"eval_samples_per_second": 162.393,
|
| 378 |
+
"eval_steps_per_second": 21.182,
|
| 379 |
+
"step": 2759
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 32.0,
|
| 383 |
+
"eval_loss": 0.44729650020599365,
|
| 384 |
+
"eval_mae": 0.5081753134727478,
|
| 385 |
+
"eval_mse": 0.44729653000831604,
|
| 386 |
+
"eval_rmse": 0.6688023209571838,
|
| 387 |
+
"eval_runtime": 0.4601,
|
| 388 |
+
"eval_samples_per_second": 149.977,
|
| 389 |
+
"eval_steps_per_second": 19.562,
|
| 390 |
+
"step": 2848
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 33.0,
|
| 394 |
+
"eval_loss": 0.43939414620399475,
|
| 395 |
+
"eval_mae": 0.5079318881034851,
|
| 396 |
+
"eval_mse": 0.43939417600631714,
|
| 397 |
+
"eval_rmse": 0.6628681421279907,
|
| 398 |
+
"eval_runtime": 0.4736,
|
| 399 |
+
"eval_samples_per_second": 145.702,
|
| 400 |
+
"eval_steps_per_second": 19.005,
|
| 401 |
+
"step": 2937
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 33.71,
|
| 405 |
+
"learning_rate": 3.258426966292135e-06,
|
| 406 |
+
"loss": 0.0532,
|
| 407 |
+
"step": 3000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 34.0,
|
| 411 |
+
"eval_loss": 0.4430878460407257,
|
| 412 |
+
"eval_mae": 0.5065318942070007,
|
| 413 |
+
"eval_mse": 0.44308778643608093,
|
| 414 |
+
"eval_rmse": 0.6656484007835388,
|
| 415 |
+
"eval_runtime": 0.4788,
|
| 416 |
+
"eval_samples_per_second": 144.103,
|
| 417 |
+
"eval_steps_per_second": 18.796,
|
| 418 |
+
"step": 3026
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 35.0,
|
| 422 |
+
"eval_loss": 0.4311515688896179,
|
| 423 |
+
"eval_mae": 0.5022226572036743,
|
| 424 |
+
"eval_mse": 0.4311515688896179,
|
| 425 |
+
"eval_rmse": 0.6566213369369507,
|
| 426 |
+
"eval_runtime": 0.47,
|
| 427 |
+
"eval_samples_per_second": 146.806,
|
| 428 |
+
"eval_steps_per_second": 19.149,
|
| 429 |
+
"step": 3115
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 36.0,
|
| 433 |
+
"eval_loss": 0.42474353313446045,
|
| 434 |
+
"eval_mae": 0.49367982149124146,
|
| 435 |
+
"eval_mse": 0.42474350333213806,
|
| 436 |
+
"eval_rmse": 0.6517235040664673,
|
| 437 |
+
"eval_runtime": 0.4548,
|
| 438 |
+
"eval_samples_per_second": 151.706,
|
| 439 |
+
"eval_steps_per_second": 19.788,
|
| 440 |
+
"step": 3204
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 37.0,
|
| 444 |
+
"eval_loss": 0.4552953541278839,
|
| 445 |
+
"eval_mae": 0.5187087655067444,
|
| 446 |
+
"eval_mse": 0.45529526472091675,
|
| 447 |
+
"eval_rmse": 0.6747556924819946,
|
| 448 |
+
"eval_runtime": 0.329,
|
| 449 |
+
"eval_samples_per_second": 209.749,
|
| 450 |
+
"eval_steps_per_second": 27.359,
|
| 451 |
+
"step": 3293
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 38.0,
|
| 455 |
+
"eval_loss": 0.42223644256591797,
|
| 456 |
+
"eval_mae": 0.4933069348335266,
|
| 457 |
+
"eval_mse": 0.4222363829612732,
|
| 458 |
+
"eval_rmse": 0.6497972011566162,
|
| 459 |
+
"eval_runtime": 0.3523,
|
| 460 |
+
"eval_samples_per_second": 195.847,
|
| 461 |
+
"eval_steps_per_second": 25.545,
|
| 462 |
+
"step": 3382
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 39.0,
|
| 466 |
+
"eval_loss": 0.4451429545879364,
|
| 467 |
+
"eval_mae": 0.5115242004394531,
|
| 468 |
+
"eval_mse": 0.4451429843902588,
|
| 469 |
+
"eval_rmse": 0.6671903729438782,
|
| 470 |
+
"eval_runtime": 0.1851,
|
| 471 |
+
"eval_samples_per_second": 372.87,
|
| 472 |
+
"eval_steps_per_second": 48.635,
|
| 473 |
+
"step": 3471
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 39.33,
|
| 477 |
+
"learning_rate": 2.1348314606741574e-06,
|
| 478 |
+
"loss": 0.0421,
|
| 479 |
+
"step": 3500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 40.0,
|
| 483 |
+
"eval_loss": 0.42086702585220337,
|
| 484 |
+
"eval_mae": 0.49490445852279663,
|
| 485 |
+
"eval_mse": 0.4208669662475586,
|
| 486 |
+
"eval_rmse": 0.6487426161766052,
|
| 487 |
+
"eval_runtime": 0.3399,
|
| 488 |
+
"eval_samples_per_second": 203.01,
|
| 489 |
+
"eval_steps_per_second": 26.48,
|
| 490 |
+
"step": 3560
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 41.0,
|
| 494 |
+
"eval_loss": 0.44048014283180237,
|
| 495 |
+
"eval_mae": 0.5092083215713501,
|
| 496 |
+
"eval_mse": 0.4404800832271576,
|
| 497 |
+
"eval_rmse": 0.6636867523193359,
|
| 498 |
+
"eval_runtime": 0.3606,
|
| 499 |
+
"eval_samples_per_second": 191.355,
|
| 500 |
+
"eval_steps_per_second": 24.959,
|
| 501 |
+
"step": 3649
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 42.0,
|
| 505 |
+
"eval_loss": 0.41600948572158813,
|
| 506 |
+
"eval_mae": 0.49518799781799316,
|
| 507 |
+
"eval_mse": 0.4160095453262329,
|
| 508 |
+
"eval_rmse": 0.6449880003929138,
|
| 509 |
+
"eval_runtime": 0.3412,
|
| 510 |
+
"eval_samples_per_second": 202.233,
|
| 511 |
+
"eval_steps_per_second": 26.378,
|
| 512 |
+
"step": 3738
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 43.0,
|
| 516 |
+
"eval_loss": 0.42693421244621277,
|
| 517 |
+
"eval_mae": 0.5002013444900513,
|
| 518 |
+
"eval_mse": 0.42693421244621277,
|
| 519 |
+
"eval_rmse": 0.6534020304679871,
|
| 520 |
+
"eval_runtime": 0.2082,
|
| 521 |
+
"eval_samples_per_second": 331.427,
|
| 522 |
+
"eval_steps_per_second": 43.23,
|
| 523 |
+
"step": 3827
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 44.0,
|
| 527 |
+
"eval_loss": 0.4115591049194336,
|
| 528 |
+
"eval_mae": 0.491961270570755,
|
| 529 |
+
"eval_mse": 0.4115590751171112,
|
| 530 |
+
"eval_rmse": 0.6415287256240845,
|
| 531 |
+
"eval_runtime": 0.3428,
|
| 532 |
+
"eval_samples_per_second": 201.27,
|
| 533 |
+
"eval_steps_per_second": 26.253,
|
| 534 |
+
"step": 3916
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 44.94,
|
| 538 |
+
"learning_rate": 1.01123595505618e-06,
|
| 539 |
+
"loss": 0.0419,
|
| 540 |
+
"step": 4000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 45.0,
|
| 544 |
+
"eval_loss": 0.41869696974754333,
|
| 545 |
+
"eval_mae": 0.500180721282959,
|
| 546 |
+
"eval_mse": 0.41869693994522095,
|
| 547 |
+
"eval_rmse": 0.6470679640769958,
|
| 548 |
+
"eval_runtime": 0.3406,
|
| 549 |
+
"eval_samples_per_second": 202.605,
|
| 550 |
+
"eval_steps_per_second": 26.427,
|
| 551 |
+
"step": 4005
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 46.0,
|
| 555 |
+
"eval_loss": 0.4199928641319275,
|
| 556 |
+
"eval_mae": 0.504236102104187,
|
| 557 |
+
"eval_mse": 0.41999292373657227,
|
| 558 |
+
"eval_rmse": 0.6480686068534851,
|
| 559 |
+
"eval_runtime": 0.3427,
|
| 560 |
+
"eval_samples_per_second": 201.361,
|
| 561 |
+
"eval_steps_per_second": 26.264,
|
| 562 |
+
"step": 4094
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 47.0,
|
| 566 |
+
"eval_loss": 0.4173473119735718,
|
| 567 |
+
"eval_mae": 0.49992823600769043,
|
| 568 |
+
"eval_mse": 0.41734734177589417,
|
| 569 |
+
"eval_rmse": 0.6460242867469788,
|
| 570 |
+
"eval_runtime": 0.3094,
|
| 571 |
+
"eval_samples_per_second": 222.982,
|
| 572 |
+
"eval_steps_per_second": 29.085,
|
| 573 |
+
"step": 4183
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 48.0,
|
| 577 |
+
"eval_loss": 0.41815370321273804,
|
| 578 |
+
"eval_mae": 0.4995117783546448,
|
| 579 |
+
"eval_mse": 0.4181537628173828,
|
| 580 |
+
"eval_rmse": 0.646648108959198,
|
| 581 |
+
"eval_runtime": 0.3301,
|
| 582 |
+
"eval_samples_per_second": 209.019,
|
| 583 |
+
"eval_steps_per_second": 27.263,
|
| 584 |
+
"step": 4272
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 49.0,
|
| 588 |
+
"eval_loss": 0.41537874937057495,
|
| 589 |
+
"eval_mae": 0.49763771891593933,
|
| 590 |
+
"eval_mse": 0.41537871956825256,
|
| 591 |
+
"eval_rmse": 0.6444988250732422,
|
| 592 |
+
"eval_runtime": 0.3396,
|
| 593 |
+
"eval_samples_per_second": 203.201,
|
| 594 |
+
"eval_steps_per_second": 26.504,
|
| 595 |
+
"step": 4361
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 50.0,
|
| 599 |
+
"eval_loss": 0.41592642664909363,
|
| 600 |
+
"eval_mae": 0.4979737401008606,
|
| 601 |
+
"eval_mse": 0.4159264862537384,
|
| 602 |
+
"eval_rmse": 0.6449236273765564,
|
| 603 |
+
"eval_runtime": 0.3167,
|
| 604 |
+
"eval_samples_per_second": 217.87,
|
| 605 |
+
"eval_steps_per_second": 28.418,
|
| 606 |
+
"step": 4450
|
| 607 |
+
}
|
| 608 |
+
],
|
| 609 |
+
"max_steps": 4450,
|
| 610 |
+
"num_train_epochs": 50,
|
| 611 |
+
"total_flos": 2354503087987200.0,
|
| 612 |
+
"trial_name": null,
|
| 613 |
+
"trial_params": null
|
| 614 |
+
}
|
checkpoint-4450/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e70d540936d1af4eab804783634188cb1039b7caf62609f969280423a545121
|
| 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 |
+
}
|
esol.out
ADDED
|
@@ -0,0 +1,438 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Some weights of the model checkpoint at data/saved_models/our_90epochs_saved_model were not used when initializing RobertaForSelfiesClassification: ['lm_head.layer_norm.bias', 'lm_head.dense.bias', 'lm_head.layer_norm.weight', 'lm_head.bias', 'lm_head.dense.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.dense.weight', 'classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'roberta.pooler.dense.weight', 'roberta.pooler.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 = 711
|
| 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 = 4450
|
| 14 |
+
***** Running Evaluation *****
|
| 15 |
+
Num examples = 69
|
| 16 |
+
Batch size = 8
|
| 17 |
+
{'eval_loss': 1.7501213550567627, 'eval_mse': 1.750120997428894, 'eval_rmse': 1.3229213953018188, 'eval_mae': 1.0687230825424194, 'eval_runtime': 0.213, 'eval_samples_per_second': 323.879, 'eval_steps_per_second': 42.245, 'epoch': 1.0}
|
| 18 |
+
Saving model checkpoint to our_esol_model/checkpoint-89
|
| 19 |
+
Configuration saved in our_esol_model/checkpoint-89/config.json
|
| 20 |
+
Model weights saved in our_esol_model/checkpoint-89/pytorch_model.bin
|
| 21 |
+
***** Running Evaluation *****
|
| 22 |
+
Num examples = 69
|
| 23 |
+
Batch size = 8
|
| 24 |
+
{'eval_loss': 0.9408809542655945, 'eval_mse': 0.9408809542655945, 'eval_rmse': 0.9699901938438416, 'eval_mae': 0.7522120475769043, 'eval_runtime': 0.4675, 'eval_samples_per_second': 147.6, 'eval_steps_per_second': 19.252, 'epoch': 2.0}
|
| 25 |
+
Saving model checkpoint to our_esol_model/checkpoint-178
|
| 26 |
+
Configuration saved in our_esol_model/checkpoint-178/config.json
|
| 27 |
+
Model weights saved in our_esol_model/checkpoint-178/pytorch_model.bin
|
| 28 |
+
Deleting older checkpoint [our_esol_model/checkpoint-89] due to args.save_total_limit
|
| 29 |
+
***** Running Evaluation *****
|
| 30 |
+
Num examples = 69
|
| 31 |
+
Batch size = 8
|
| 32 |
+
{'eval_loss': 0.7912163138389587, 'eval_mse': 0.7912163734436035, 'eval_rmse': 0.8895034193992615, 'eval_mae': 0.7013395428657532, 'eval_runtime': 0.4829, 'eval_samples_per_second': 142.893, 'eval_steps_per_second': 18.638, 'epoch': 3.0}
|
| 33 |
+
Saving model checkpoint to our_esol_model/checkpoint-267
|
| 34 |
+
Configuration saved in our_esol_model/checkpoint-267/config.json
|
| 35 |
+
Model weights saved in our_esol_model/checkpoint-267/pytorch_model.bin
|
| 36 |
+
Deleting older checkpoint [our_esol_model/checkpoint-178] due to args.save_total_limit
|
| 37 |
+
***** Running Evaluation *****
|
| 38 |
+
Num examples = 69
|
| 39 |
+
Batch size = 8
|
| 40 |
+
{'eval_loss': 0.7405096292495728, 'eval_mse': 0.7405097484588623, 'eval_rmse': 0.8605287671089172, 'eval_mae': 0.6587470769882202, 'eval_runtime': 0.4491, 'eval_samples_per_second': 153.654, 'eval_steps_per_second': 20.042, 'epoch': 4.0}
|
| 41 |
+
Saving model checkpoint to our_esol_model/checkpoint-356
|
| 42 |
+
Configuration saved in our_esol_model/checkpoint-356/config.json
|
| 43 |
+
Model weights saved in our_esol_model/checkpoint-356/pytorch_model.bin
|
| 44 |
+
Deleting older checkpoint [our_esol_model/checkpoint-267] due to args.save_total_limit
|
| 45 |
+
***** Running Evaluation *****
|
| 46 |
+
Num examples = 69
|
| 47 |
+
Batch size = 8
|
| 48 |
+
{'eval_loss': 0.6923832297325134, 'eval_mse': 0.6923832893371582, 'eval_rmse': 0.832095742225647, 'eval_mae': 0.6610296964645386, 'eval_runtime': 0.4191, 'eval_samples_per_second': 164.64, 'eval_steps_per_second': 21.475, 'epoch': 5.0}
|
| 49 |
+
Saving model checkpoint to our_esol_model/checkpoint-445
|
| 50 |
+
Configuration saved in our_esol_model/checkpoint-445/config.json
|
| 51 |
+
Model weights saved in our_esol_model/checkpoint-445/pytorch_model.bin
|
| 52 |
+
Deleting older checkpoint [our_esol_model/checkpoint-356] due to args.save_total_limit
|
| 53 |
+
{'loss': 0.9104, 'learning_rate': 8.876404494382023e-06, 'epoch': 5.62}
|
| 54 |
+
***** Running Evaluation *****
|
| 55 |
+
Num examples = 69
|
| 56 |
+
Batch size = 8
|
| 57 |
+
{'eval_loss': 0.6709772944450378, 'eval_mse': 0.6709771752357483, 'eval_rmse': 0.8191319704055786, 'eval_mae': 0.6442688703536987, 'eval_runtime': 0.4743, 'eval_samples_per_second': 145.467, 'eval_steps_per_second': 18.974, 'epoch': 6.0}
|
| 58 |
+
Saving model checkpoint to our_esol_model/checkpoint-534
|
| 59 |
+
Configuration saved in our_esol_model/checkpoint-534/config.json
|
| 60 |
+
Model weights saved in our_esol_model/checkpoint-534/pytorch_model.bin
|
| 61 |
+
Deleting older checkpoint [our_esol_model/checkpoint-445] due to args.save_total_limit
|
| 62 |
+
***** Running Evaluation *****
|
| 63 |
+
Num examples = 69
|
| 64 |
+
Batch size = 8
|
| 65 |
+
{'eval_loss': 0.5820761322975159, 'eval_mse': 0.5820761919021606, 'eval_rmse': 0.7629391551017761, 'eval_mae': 0.6152850389480591, 'eval_runtime': 0.364, 'eval_samples_per_second': 189.553, 'eval_steps_per_second': 24.724, 'epoch': 7.0}
|
| 66 |
+
Saving model checkpoint to our_esol_model/checkpoint-623
|
| 67 |
+
Configuration saved in our_esol_model/checkpoint-623/config.json
|
| 68 |
+
Model weights saved in our_esol_model/checkpoint-623/pytorch_model.bin
|
| 69 |
+
Deleting older checkpoint [our_esol_model/checkpoint-534] due to args.save_total_limit
|
| 70 |
+
***** Running Evaluation *****
|
| 71 |
+
Num examples = 69
|
| 72 |
+
Batch size = 8
|
| 73 |
+
{'eval_loss': 0.49572908878326416, 'eval_mse': 0.49572914838790894, 'eval_rmse': 0.70408034324646, 'eval_mae': 0.5509689450263977, 'eval_runtime': 0.4466, 'eval_samples_per_second': 154.492, 'eval_steps_per_second': 20.151, 'epoch': 8.0}
|
| 74 |
+
Saving model checkpoint to our_esol_model/checkpoint-712
|
| 75 |
+
Configuration saved in our_esol_model/checkpoint-712/config.json
|
| 76 |
+
Model weights saved in our_esol_model/checkpoint-712/pytorch_model.bin
|
| 77 |
+
Deleting older checkpoint [our_esol_model/checkpoint-623] due to args.save_total_limit
|
| 78 |
+
***** Running Evaluation *****
|
| 79 |
+
Num examples = 69
|
| 80 |
+
Batch size = 8
|
| 81 |
+
{'eval_loss': 0.5924321413040161, 'eval_mse': 0.5924323201179504, 'eval_rmse': 0.7696962356567383, 'eval_mae': 0.6066040396690369, 'eval_runtime': 0.4645, 'eval_samples_per_second': 148.549, 'eval_steps_per_second': 19.376, 'epoch': 9.0}
|
| 82 |
+
Saving model checkpoint to our_esol_model/checkpoint-801
|
| 83 |
+
Configuration saved in our_esol_model/checkpoint-801/config.json
|
| 84 |
+
Model weights saved in our_esol_model/checkpoint-801/pytorch_model.bin
|
| 85 |
+
Deleting older checkpoint [our_esol_model/checkpoint-712] due to args.save_total_limit
|
| 86 |
+
***** Running Evaluation *****
|
| 87 |
+
Num examples = 69
|
| 88 |
+
Batch size = 8
|
| 89 |
+
{'eval_loss': 0.4954969882965088, 'eval_mse': 0.4954971671104431, 'eval_rmse': 0.7039155960083008, 'eval_mae': 0.5473751425743103, 'eval_runtime': 0.3698, 'eval_samples_per_second': 186.61, 'eval_steps_per_second': 24.34, 'epoch': 10.0}
|
| 90 |
+
Saving model checkpoint to our_esol_model/checkpoint-890
|
| 91 |
+
Configuration saved in our_esol_model/checkpoint-890/config.json
|
| 92 |
+
Model weights saved in our_esol_model/checkpoint-890/pytorch_model.bin
|
| 93 |
+
Deleting older checkpoint [our_esol_model/checkpoint-801] due to args.save_total_limit
|
| 94 |
+
***** Running Evaluation *****
|
| 95 |
+
Num examples = 69
|
| 96 |
+
Batch size = 8
|
| 97 |
+
{'eval_loss': 0.5200049877166748, 'eval_mse': 0.52000492811203, 'eval_rmse': 0.7211136817932129, 'eval_mae': 0.5685440897941589, 'eval_runtime': 0.4266, 'eval_samples_per_second': 161.746, 'eval_steps_per_second': 21.097, 'epoch': 11.0}
|
| 98 |
+
Saving model checkpoint to our_esol_model/checkpoint-979
|
| 99 |
+
Configuration saved in our_esol_model/checkpoint-979/config.json
|
| 100 |
+
Model weights saved in our_esol_model/checkpoint-979/pytorch_model.bin
|
| 101 |
+
Deleting older checkpoint [our_esol_model/checkpoint-890] due to args.save_total_limit
|
| 102 |
+
{'loss': 0.128, 'learning_rate': 7.752808988764046e-06, 'epoch': 11.24}
|
| 103 |
+
***** Running Evaluation *****
|
| 104 |
+
Num examples = 69
|
| 105 |
+
Batch size = 8
|
| 106 |
+
{'eval_loss': 0.43686971068382263, 'eval_mse': 0.436869740486145, 'eval_rmse': 0.6609612107276917, 'eval_mae': 0.5061944723129272, 'eval_runtime': 0.4821, 'eval_samples_per_second': 143.124, 'eval_steps_per_second': 18.668, 'epoch': 12.0}
|
| 107 |
+
Saving model checkpoint to our_esol_model/checkpoint-1068
|
| 108 |
+
Configuration saved in our_esol_model/checkpoint-1068/config.json
|
| 109 |
+
Model weights saved in our_esol_model/checkpoint-1068/pytorch_model.bin
|
| 110 |
+
Deleting older checkpoint [our_esol_model/checkpoint-979] due to args.save_total_limit
|
| 111 |
+
***** Running Evaluation *****
|
| 112 |
+
Num examples = 69
|
| 113 |
+
Batch size = 8
|
| 114 |
+
{'eval_loss': 0.41416943073272705, 'eval_mse': 0.41416940093040466, 'eval_rmse': 0.6435599327087402, 'eval_mae': 0.46771711111068726, 'eval_runtime': 0.4624, 'eval_samples_per_second': 149.23, 'eval_steps_per_second': 19.465, 'epoch': 13.0}
|
| 115 |
+
Saving model checkpoint to our_esol_model/checkpoint-1157
|
| 116 |
+
Configuration saved in our_esol_model/checkpoint-1157/config.json
|
| 117 |
+
Model weights saved in our_esol_model/checkpoint-1157/pytorch_model.bin
|
| 118 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1068] due to args.save_total_limit
|
| 119 |
+
***** Running Evaluation *****
|
| 120 |
+
Num examples = 69
|
| 121 |
+
Batch size = 8
|
| 122 |
+
{'eval_loss': 0.40698668360710144, 'eval_mse': 0.4069867730140686, 'eval_rmse': 0.6379551291465759, 'eval_mae': 0.45521026849746704, 'eval_runtime': 0.4757, 'eval_samples_per_second': 145.044, 'eval_steps_per_second': 18.919, 'epoch': 14.0}
|
| 123 |
+
Saving model checkpoint to our_esol_model/checkpoint-1246
|
| 124 |
+
Configuration saved in our_esol_model/checkpoint-1246/config.json
|
| 125 |
+
Model weights saved in our_esol_model/checkpoint-1246/pytorch_model.bin
|
| 126 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1157] due to args.save_total_limit
|
| 127 |
+
***** Running Evaluation *****
|
| 128 |
+
Num examples = 69
|
| 129 |
+
Batch size = 8
|
| 130 |
+
{'eval_loss': 0.49930572509765625, 'eval_mse': 0.4993056654930115, 'eval_rmse': 0.7066156268119812, 'eval_mae': 0.5383840799331665, 'eval_runtime': 0.4656, 'eval_samples_per_second': 148.181, 'eval_steps_per_second': 19.328, 'epoch': 15.0}
|
| 131 |
+
Saving model checkpoint to our_esol_model/checkpoint-1335
|
| 132 |
+
Configuration saved in our_esol_model/checkpoint-1335/config.json
|
| 133 |
+
Model weights saved in our_esol_model/checkpoint-1335/pytorch_model.bin
|
| 134 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1246] due to args.save_total_limit
|
| 135 |
+
***** Running Evaluation *****
|
| 136 |
+
Num examples = 69
|
| 137 |
+
Batch size = 8
|
| 138 |
+
{'eval_loss': 0.5578888654708862, 'eval_mse': 0.5578888058662415, 'eval_rmse': 0.746919572353363, 'eval_mae': 0.585189163684845, 'eval_runtime': 0.4755, 'eval_samples_per_second': 145.098, 'eval_steps_per_second': 18.926, 'epoch': 16.0}
|
| 139 |
+
Saving model checkpoint to our_esol_model/checkpoint-1424
|
| 140 |
+
Configuration saved in our_esol_model/checkpoint-1424/config.json
|
| 141 |
+
Model weights saved in our_esol_model/checkpoint-1424/pytorch_model.bin
|
| 142 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1335] due to args.save_total_limit
|
| 143 |
+
{'loss': 0.0895, 'learning_rate': 6.629213483146067e-06, 'epoch': 16.85}
|
| 144 |
+
***** Running Evaluation *****
|
| 145 |
+
Num examples = 69
|
| 146 |
+
Batch size = 8
|
| 147 |
+
{'eval_loss': 0.5015009045600891, 'eval_mse': 0.5015009641647339, 'eval_rmse': 0.708167314529419, 'eval_mae': 0.561897337436676, 'eval_runtime': 0.3883, 'eval_samples_per_second': 177.714, 'eval_steps_per_second': 23.18, 'epoch': 17.0}
|
| 148 |
+
Saving model checkpoint to our_esol_model/checkpoint-1513
|
| 149 |
+
Configuration saved in our_esol_model/checkpoint-1513/config.json
|
| 150 |
+
Model weights saved in our_esol_model/checkpoint-1513/pytorch_model.bin
|
| 151 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1424] due to args.save_total_limit
|
| 152 |
+
***** Running Evaluation *****
|
| 153 |
+
Num examples = 69
|
| 154 |
+
Batch size = 8
|
| 155 |
+
{'eval_loss': 0.4590393602848053, 'eval_mse': 0.45903947949409485, 'eval_rmse': 0.6775245070457458, 'eval_mae': 0.5263462066650391, 'eval_runtime': 0.4835, 'eval_samples_per_second': 142.705, 'eval_steps_per_second': 18.614, 'epoch': 18.0}
|
| 156 |
+
Saving model checkpoint to our_esol_model/checkpoint-1602
|
| 157 |
+
Configuration saved in our_esol_model/checkpoint-1602/config.json
|
| 158 |
+
Model weights saved in our_esol_model/checkpoint-1602/pytorch_model.bin
|
| 159 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1513] due to args.save_total_limit
|
| 160 |
+
***** Running Evaluation *****
|
| 161 |
+
Num examples = 69
|
| 162 |
+
Batch size = 8
|
| 163 |
+
{'eval_loss': 0.4880666434764862, 'eval_mse': 0.4880666732788086, 'eval_rmse': 0.698617696762085, 'eval_mae': 0.5377508997917175, 'eval_runtime': 0.4715, 'eval_samples_per_second': 146.34, 'eval_steps_per_second': 19.088, 'epoch': 19.0}
|
| 164 |
+
Saving model checkpoint to our_esol_model/checkpoint-1691
|
| 165 |
+
Configuration saved in our_esol_model/checkpoint-1691/config.json
|
| 166 |
+
Model weights saved in our_esol_model/checkpoint-1691/pytorch_model.bin
|
| 167 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1602] due to args.save_total_limit
|
| 168 |
+
***** Running Evaluation *****
|
| 169 |
+
Num examples = 69
|
| 170 |
+
Batch size = 8
|
| 171 |
+
{'eval_loss': 0.3925124704837799, 'eval_mse': 0.3925124406814575, 'eval_rmse': 0.6265081167221069, 'eval_mae': 0.46625784039497375, 'eval_runtime': 0.3158, 'eval_samples_per_second': 218.521, 'eval_steps_per_second': 28.503, 'epoch': 20.0}
|
| 172 |
+
Saving model checkpoint to our_esol_model/checkpoint-1780
|
| 173 |
+
Configuration saved in our_esol_model/checkpoint-1780/config.json
|
| 174 |
+
Model weights saved in our_esol_model/checkpoint-1780/pytorch_model.bin
|
| 175 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1691] due to args.save_total_limit
|
| 176 |
+
***** Running Evaluation *****
|
| 177 |
+
Num examples = 69
|
| 178 |
+
Batch size = 8
|
| 179 |
+
{'eval_loss': 0.4392476975917816, 'eval_mse': 0.4392476975917816, 'eval_rmse': 0.6627576351165771, 'eval_mae': 0.5062677264213562, 'eval_runtime': 0.4321, 'eval_samples_per_second': 159.696, 'eval_steps_per_second': 20.83, 'epoch': 21.0}
|
| 180 |
+
Saving model checkpoint to our_esol_model/checkpoint-1869
|
| 181 |
+
Configuration saved in our_esol_model/checkpoint-1869/config.json
|
| 182 |
+
Model weights saved in our_esol_model/checkpoint-1869/pytorch_model.bin
|
| 183 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1780] due to args.save_total_limit
|
| 184 |
+
***** Running Evaluation *****
|
| 185 |
+
Num examples = 69
|
| 186 |
+
Batch size = 8
|
| 187 |
+
{'eval_loss': 0.42705094814300537, 'eval_mse': 0.42705097794532776, 'eval_rmse': 0.6534913778305054, 'eval_mae': 0.48886218667030334, 'eval_runtime': 0.3907, 'eval_samples_per_second': 176.595, 'eval_steps_per_second': 23.034, 'epoch': 22.0}
|
| 188 |
+
Saving model checkpoint to our_esol_model/checkpoint-1958
|
| 189 |
+
Configuration saved in our_esol_model/checkpoint-1958/config.json
|
| 190 |
+
Model weights saved in our_esol_model/checkpoint-1958/pytorch_model.bin
|
| 191 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1869] due to args.save_total_limit
|
| 192 |
+
{'loss': 0.0694, 'learning_rate': 5.50561797752809e-06, 'epoch': 22.47}
|
| 193 |
+
***** Running Evaluation *****
|
| 194 |
+
Num examples = 69
|
| 195 |
+
Batch size = 8
|
| 196 |
+
{'eval_loss': 0.40933796763420105, 'eval_mse': 0.4093380868434906, 'eval_rmse': 0.6397953629493713, 'eval_mae': 0.4783601760864258, 'eval_runtime': 0.3371, 'eval_samples_per_second': 204.706, 'eval_steps_per_second': 26.701, 'epoch': 23.0}
|
| 197 |
+
Saving model checkpoint to our_esol_model/checkpoint-2047
|
| 198 |
+
Configuration saved in our_esol_model/checkpoint-2047/config.json
|
| 199 |
+
Model weights saved in our_esol_model/checkpoint-2047/pytorch_model.bin
|
| 200 |
+
Deleting older checkpoint [our_esol_model/checkpoint-1958] due to args.save_total_limit
|
| 201 |
+
***** Running Evaluation *****
|
| 202 |
+
Num examples = 69
|
| 203 |
+
Batch size = 8
|
| 204 |
+
{'eval_loss': 0.42077454924583435, 'eval_mse': 0.42077454924583435, 'eval_rmse': 0.6486713886260986, 'eval_mae': 0.49500545859336853, 'eval_runtime': 0.4775, 'eval_samples_per_second': 144.493, 'eval_steps_per_second': 18.847, 'epoch': 24.0}
|
| 205 |
+
Saving model checkpoint to our_esol_model/checkpoint-2136
|
| 206 |
+
Configuration saved in our_esol_model/checkpoint-2136/config.json
|
| 207 |
+
Model weights saved in our_esol_model/checkpoint-2136/pytorch_model.bin
|
| 208 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2047] due to args.save_total_limit
|
| 209 |
+
***** Running Evaluation *****
|
| 210 |
+
Num examples = 69
|
| 211 |
+
Batch size = 8
|
| 212 |
+
{'eval_loss': 0.40650996565818787, 'eval_mse': 0.4065099358558655, 'eval_rmse': 0.6375812888145447, 'eval_mae': 0.4869938790798187, 'eval_runtime': 0.4751, 'eval_samples_per_second': 145.227, 'eval_steps_per_second': 18.943, 'epoch': 25.0}
|
| 213 |
+
Saving model checkpoint to our_esol_model/checkpoint-2225
|
| 214 |
+
Configuration saved in our_esol_model/checkpoint-2225/config.json
|
| 215 |
+
Model weights saved in our_esol_model/checkpoint-2225/pytorch_model.bin
|
| 216 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2136] due to args.save_total_limit
|
| 217 |
+
***** Running Evaluation *****
|
| 218 |
+
Num examples = 69
|
| 219 |
+
Batch size = 8
|
| 220 |
+
{'eval_loss': 0.4467940032482147, 'eval_mse': 0.44679397344589233, 'eval_rmse': 0.668426513671875, 'eval_mae': 0.5186977386474609, 'eval_runtime': 0.4523, 'eval_samples_per_second': 152.552, 'eval_steps_per_second': 19.898, 'epoch': 26.0}
|
| 221 |
+
Saving model checkpoint to our_esol_model/checkpoint-2314
|
| 222 |
+
Configuration saved in our_esol_model/checkpoint-2314/config.json
|
| 223 |
+
Model weights saved in our_esol_model/checkpoint-2314/pytorch_model.bin
|
| 224 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2225] due to args.save_total_limit
|
| 225 |
+
***** Running Evaluation *****
|
| 226 |
+
Num examples = 69
|
| 227 |
+
Batch size = 8
|
| 228 |
+
{'eval_loss': 0.448551744222641, 'eval_mse': 0.4485517740249634, 'eval_rmse': 0.6697400808334351, 'eval_mae': 0.5286442041397095, 'eval_runtime': 0.3607, 'eval_samples_per_second': 191.288, 'eval_steps_per_second': 24.951, 'epoch': 27.0}
|
| 229 |
+
Saving model checkpoint to our_esol_model/checkpoint-2403
|
| 230 |
+
Configuration saved in our_esol_model/checkpoint-2403/config.json
|
| 231 |
+
Model weights saved in our_esol_model/checkpoint-2403/pytorch_model.bin
|
| 232 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2314] due to args.save_total_limit
|
| 233 |
+
***** Running Evaluation *****
|
| 234 |
+
Num examples = 69
|
| 235 |
+
Batch size = 8
|
| 236 |
+
{'eval_loss': 0.4263148605823517, 'eval_mse': 0.4263148009777069, 'eval_rmse': 0.6529278755187988, 'eval_mae': 0.5110523700714111, 'eval_runtime': 0.4741, 'eval_samples_per_second': 145.544, 'eval_steps_per_second': 18.984, 'epoch': 28.0}
|
| 237 |
+
Saving model checkpoint to our_esol_model/checkpoint-2492
|
| 238 |
+
Configuration saved in our_esol_model/checkpoint-2492/config.json
|
| 239 |
+
Model weights saved in our_esol_model/checkpoint-2492/pytorch_model.bin
|
| 240 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2403] due to args.save_total_limit
|
| 241 |
+
{'loss': 0.0575, 'learning_rate': 4.382022471910113e-06, 'epoch': 28.09}
|
| 242 |
+
***** Running Evaluation *****
|
| 243 |
+
Num examples = 69
|
| 244 |
+
Batch size = 8
|
| 245 |
+
{'eval_loss': 0.4624464213848114, 'eval_mse': 0.462446391582489, 'eval_rmse': 0.6800341010093689, 'eval_mae': 0.5141972303390503, 'eval_runtime': 0.4737, 'eval_samples_per_second': 145.658, 'eval_steps_per_second': 18.999, 'epoch': 29.0}
|
| 246 |
+
Saving model checkpoint to our_esol_model/checkpoint-2581
|
| 247 |
+
Configuration saved in our_esol_model/checkpoint-2581/config.json
|
| 248 |
+
Model weights saved in our_esol_model/checkpoint-2581/pytorch_model.bin
|
| 249 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2492] due to args.save_total_limit
|
| 250 |
+
***** Running Evaluation *****
|
| 251 |
+
Num examples = 69
|
| 252 |
+
Batch size = 8
|
| 253 |
+
{'eval_loss': 0.4065593481063843, 'eval_mse': 0.40655940771102905, 'eval_rmse': 0.6376200914382935, 'eval_mae': 0.4846087396144867, 'eval_runtime': 0.3326, 'eval_samples_per_second': 207.482, 'eval_steps_per_second': 27.063, 'epoch': 30.0}
|
| 254 |
+
Saving model checkpoint to our_esol_model/checkpoint-2670
|
| 255 |
+
Configuration saved in our_esol_model/checkpoint-2670/config.json
|
| 256 |
+
Model weights saved in our_esol_model/checkpoint-2670/pytorch_model.bin
|
| 257 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2581] due to args.save_total_limit
|
| 258 |
+
***** Running Evaluation *****
|
| 259 |
+
Num examples = 69
|
| 260 |
+
Batch size = 8
|
| 261 |
+
{'eval_loss': 0.4373004138469696, 'eval_mse': 0.437300443649292, 'eval_rmse': 0.6612869501113892, 'eval_mae': 0.5060880780220032, 'eval_runtime': 0.4249, 'eval_samples_per_second': 162.393, 'eval_steps_per_second': 21.182, 'epoch': 31.0}
|
| 262 |
+
Saving model checkpoint to our_esol_model/checkpoint-2759
|
| 263 |
+
Configuration saved in our_esol_model/checkpoint-2759/config.json
|
| 264 |
+
Model weights saved in our_esol_model/checkpoint-2759/pytorch_model.bin
|
| 265 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2670] due to args.save_total_limit
|
| 266 |
+
***** Running Evaluation *****
|
| 267 |
+
Num examples = 69
|
| 268 |
+
Batch size = 8
|
| 269 |
+
{'eval_loss': 0.44729650020599365, 'eval_mse': 0.44729653000831604, 'eval_rmse': 0.6688023209571838, 'eval_mae': 0.5081753134727478, 'eval_runtime': 0.4601, 'eval_samples_per_second': 149.977, 'eval_steps_per_second': 19.562, 'epoch': 32.0}
|
| 270 |
+
Saving model checkpoint to our_esol_model/checkpoint-2848
|
| 271 |
+
Configuration saved in our_esol_model/checkpoint-2848/config.json
|
| 272 |
+
Model weights saved in our_esol_model/checkpoint-2848/pytorch_model.bin
|
| 273 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2759] due to args.save_total_limit
|
| 274 |
+
***** Running Evaluation *****
|
| 275 |
+
Num examples = 69
|
| 276 |
+
Batch size = 8
|
| 277 |
+
{'eval_loss': 0.43939414620399475, 'eval_mse': 0.43939417600631714, 'eval_rmse': 0.6628681421279907, 'eval_mae': 0.5079318881034851, 'eval_runtime': 0.4736, 'eval_samples_per_second': 145.702, 'eval_steps_per_second': 19.005, 'epoch': 33.0}
|
| 278 |
+
Saving model checkpoint to our_esol_model/checkpoint-2937
|
| 279 |
+
Configuration saved in our_esol_model/checkpoint-2937/config.json
|
| 280 |
+
Model weights saved in our_esol_model/checkpoint-2937/pytorch_model.bin
|
| 281 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2848] due to args.save_total_limit
|
| 282 |
+
{'loss': 0.0532, 'learning_rate': 3.258426966292135e-06, 'epoch': 33.71}
|
| 283 |
+
***** Running Evaluation *****
|
| 284 |
+
Num examples = 69
|
| 285 |
+
Batch size = 8
|
| 286 |
+
{'eval_loss': 0.4430878460407257, 'eval_mse': 0.44308778643608093, 'eval_rmse': 0.6656484007835388, 'eval_mae': 0.5065318942070007, 'eval_runtime': 0.4788, 'eval_samples_per_second': 144.103, 'eval_steps_per_second': 18.796, 'epoch': 34.0}
|
| 287 |
+
Saving model checkpoint to our_esol_model/checkpoint-3026
|
| 288 |
+
Configuration saved in our_esol_model/checkpoint-3026/config.json
|
| 289 |
+
Model weights saved in our_esol_model/checkpoint-3026/pytorch_model.bin
|
| 290 |
+
Deleting older checkpoint [our_esol_model/checkpoint-2937] due to args.save_total_limit
|
| 291 |
+
***** Running Evaluation *****
|
| 292 |
+
Num examples = 69
|
| 293 |
+
Batch size = 8
|
| 294 |
+
{'eval_loss': 0.4311515688896179, 'eval_mse': 0.4311515688896179, 'eval_rmse': 0.6566213369369507, 'eval_mae': 0.5022226572036743, 'eval_runtime': 0.47, 'eval_samples_per_second': 146.806, 'eval_steps_per_second': 19.149, 'epoch': 35.0}
|
| 295 |
+
Saving model checkpoint to our_esol_model/checkpoint-3115
|
| 296 |
+
Configuration saved in our_esol_model/checkpoint-3115/config.json
|
| 297 |
+
Model weights saved in our_esol_model/checkpoint-3115/pytorch_model.bin
|
| 298 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3026] due to args.save_total_limit
|
| 299 |
+
***** Running Evaluation *****
|
| 300 |
+
Num examples = 69
|
| 301 |
+
Batch size = 8
|
| 302 |
+
{'eval_loss': 0.42474353313446045, 'eval_mse': 0.42474350333213806, 'eval_rmse': 0.6517235040664673, 'eval_mae': 0.49367982149124146, 'eval_runtime': 0.4548, 'eval_samples_per_second': 151.706, 'eval_steps_per_second': 19.788, 'epoch': 36.0}
|
| 303 |
+
Saving model checkpoint to our_esol_model/checkpoint-3204
|
| 304 |
+
Configuration saved in our_esol_model/checkpoint-3204/config.json
|
| 305 |
+
Model weights saved in our_esol_model/checkpoint-3204/pytorch_model.bin
|
| 306 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3115] due to args.save_total_limit
|
| 307 |
+
***** Running Evaluation *****
|
| 308 |
+
Num examples = 69
|
| 309 |
+
Batch size = 8
|
| 310 |
+
{'eval_loss': 0.4552953541278839, 'eval_mse': 0.45529526472091675, 'eval_rmse': 0.6747556924819946, 'eval_mae': 0.5187087655067444, 'eval_runtime': 0.329, 'eval_samples_per_second': 209.749, 'eval_steps_per_second': 27.359, 'epoch': 37.0}
|
| 311 |
+
Saving model checkpoint to our_esol_model/checkpoint-3293
|
| 312 |
+
Configuration saved in our_esol_model/checkpoint-3293/config.json
|
| 313 |
+
Model weights saved in our_esol_model/checkpoint-3293/pytorch_model.bin
|
| 314 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3204] due to args.save_total_limit
|
| 315 |
+
***** Running Evaluation *****
|
| 316 |
+
Num examples = 69
|
| 317 |
+
Batch size = 8
|
| 318 |
+
{'eval_loss': 0.42223644256591797, 'eval_mse': 0.4222363829612732, 'eval_rmse': 0.6497972011566162, 'eval_mae': 0.4933069348335266, 'eval_runtime': 0.3523, 'eval_samples_per_second': 195.847, 'eval_steps_per_second': 25.545, 'epoch': 38.0}
|
| 319 |
+
Saving model checkpoint to our_esol_model/checkpoint-3382
|
| 320 |
+
Configuration saved in our_esol_model/checkpoint-3382/config.json
|
| 321 |
+
Model weights saved in our_esol_model/checkpoint-3382/pytorch_model.bin
|
| 322 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3293] due to args.save_total_limit
|
| 323 |
+
***** Running Evaluation *****
|
| 324 |
+
Num examples = 69
|
| 325 |
+
Batch size = 8
|
| 326 |
+
{'eval_loss': 0.4451429545879364, 'eval_mse': 0.4451429843902588, 'eval_rmse': 0.6671903729438782, 'eval_mae': 0.5115242004394531, 'eval_runtime': 0.1851, 'eval_samples_per_second': 372.87, 'eval_steps_per_second': 48.635, 'epoch': 39.0}
|
| 327 |
+
Saving model checkpoint to our_esol_model/checkpoint-3471
|
| 328 |
+
Configuration saved in our_esol_model/checkpoint-3471/config.json
|
| 329 |
+
Model weights saved in our_esol_model/checkpoint-3471/pytorch_model.bin
|
| 330 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3382] due to args.save_total_limit
|
| 331 |
+
{'loss': 0.0421, 'learning_rate': 2.1348314606741574e-06, 'epoch': 39.33}
|
| 332 |
+
***** Running Evaluation *****
|
| 333 |
+
Num examples = 69
|
| 334 |
+
Batch size = 8
|
| 335 |
+
{'eval_loss': 0.42086702585220337, 'eval_mse': 0.4208669662475586, 'eval_rmse': 0.6487426161766052, 'eval_mae': 0.49490445852279663, 'eval_runtime': 0.3399, 'eval_samples_per_second': 203.01, 'eval_steps_per_second': 26.48, 'epoch': 40.0}
|
| 336 |
+
Saving model checkpoint to our_esol_model/checkpoint-3560
|
| 337 |
+
Configuration saved in our_esol_model/checkpoint-3560/config.json
|
| 338 |
+
Model weights saved in our_esol_model/checkpoint-3560/pytorch_model.bin
|
| 339 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3471] due to args.save_total_limit
|
| 340 |
+
***** Running Evaluation *****
|
| 341 |
+
Num examples = 69
|
| 342 |
+
Batch size = 8
|
| 343 |
+
{'eval_loss': 0.44048014283180237, 'eval_mse': 0.4404800832271576, 'eval_rmse': 0.6636867523193359, 'eval_mae': 0.5092083215713501, 'eval_runtime': 0.3606, 'eval_samples_per_second': 191.355, 'eval_steps_per_second': 24.959, 'epoch': 41.0}
|
| 344 |
+
Saving model checkpoint to our_esol_model/checkpoint-3649
|
| 345 |
+
Configuration saved in our_esol_model/checkpoint-3649/config.json
|
| 346 |
+
Model weights saved in our_esol_model/checkpoint-3649/pytorch_model.bin
|
| 347 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3560] due to args.save_total_limit
|
| 348 |
+
***** Running Evaluation *****
|
| 349 |
+
Num examples = 69
|
| 350 |
+
Batch size = 8
|
| 351 |
+
{'eval_loss': 0.41600948572158813, 'eval_mse': 0.4160095453262329, 'eval_rmse': 0.6449880003929138, 'eval_mae': 0.49518799781799316, 'eval_runtime': 0.3412, 'eval_samples_per_second': 202.233, 'eval_steps_per_second': 26.378, 'epoch': 42.0}
|
| 352 |
+
Saving model checkpoint to our_esol_model/checkpoint-3738
|
| 353 |
+
Configuration saved in our_esol_model/checkpoint-3738/config.json
|
| 354 |
+
Model weights saved in our_esol_model/checkpoint-3738/pytorch_model.bin
|
| 355 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3649] due to args.save_total_limit
|
| 356 |
+
***** Running Evaluation *****
|
| 357 |
+
Num examples = 69
|
| 358 |
+
Batch size = 8
|
| 359 |
+
{'eval_loss': 0.42693421244621277, 'eval_mse': 0.42693421244621277, 'eval_rmse': 0.6534020304679871, 'eval_mae': 0.5002013444900513, 'eval_runtime': 0.2082, 'eval_samples_per_second': 331.427, 'eval_steps_per_second': 43.23, 'epoch': 43.0}
|
| 360 |
+
Saving model checkpoint to our_esol_model/checkpoint-3827
|
| 361 |
+
Configuration saved in our_esol_model/checkpoint-3827/config.json
|
| 362 |
+
Model weights saved in our_esol_model/checkpoint-3827/pytorch_model.bin
|
| 363 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3738] due to args.save_total_limit
|
| 364 |
+
***** Running Evaluation *****
|
| 365 |
+
Num examples = 69
|
| 366 |
+
Batch size = 8
|
| 367 |
+
{'eval_loss': 0.4115591049194336, 'eval_mse': 0.4115590751171112, 'eval_rmse': 0.6415287256240845, 'eval_mae': 0.491961270570755, 'eval_runtime': 0.3428, 'eval_samples_per_second': 201.27, 'eval_steps_per_second': 26.253, 'epoch': 44.0}
|
| 368 |
+
Saving model checkpoint to our_esol_model/checkpoint-3916
|
| 369 |
+
Configuration saved in our_esol_model/checkpoint-3916/config.json
|
| 370 |
+
Model weights saved in our_esol_model/checkpoint-3916/pytorch_model.bin
|
| 371 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3827] due to args.save_total_limit
|
| 372 |
+
{'loss': 0.0419, 'learning_rate': 1.01123595505618e-06, 'epoch': 44.94}
|
| 373 |
+
***** Running Evaluation *****
|
| 374 |
+
Num examples = 69
|
| 375 |
+
Batch size = 8
|
| 376 |
+
{'eval_loss': 0.41869696974754333, 'eval_mse': 0.41869693994522095, 'eval_rmse': 0.6470679640769958, 'eval_mae': 0.500180721282959, 'eval_runtime': 0.3406, 'eval_samples_per_second': 202.605, 'eval_steps_per_second': 26.427, 'epoch': 45.0}
|
| 377 |
+
Saving model checkpoint to our_esol_model/checkpoint-4005
|
| 378 |
+
Configuration saved in our_esol_model/checkpoint-4005/config.json
|
| 379 |
+
Model weights saved in our_esol_model/checkpoint-4005/pytorch_model.bin
|
| 380 |
+
Deleting older checkpoint [our_esol_model/checkpoint-3916] due to args.save_total_limit
|
| 381 |
+
***** Running Evaluation *****
|
| 382 |
+
Num examples = 69
|
| 383 |
+
Batch size = 8
|
| 384 |
+
{'eval_loss': 0.4199928641319275, 'eval_mse': 0.41999292373657227, 'eval_rmse': 0.6480686068534851, 'eval_mae': 0.504236102104187, 'eval_runtime': 0.3427, 'eval_samples_per_second': 201.361, 'eval_steps_per_second': 26.264, 'epoch': 46.0}
|
| 385 |
+
Saving model checkpoint to our_esol_model/checkpoint-4094
|
| 386 |
+
Configuration saved in our_esol_model/checkpoint-4094/config.json
|
| 387 |
+
Model weights saved in our_esol_model/checkpoint-4094/pytorch_model.bin
|
| 388 |
+
Deleting older checkpoint [our_esol_model/checkpoint-4005] due to args.save_total_limit
|
| 389 |
+
***** Running Evaluation *****
|
| 390 |
+
Num examples = 69
|
| 391 |
+
Batch size = 8
|
| 392 |
+
{'eval_loss': 0.4173473119735718, 'eval_mse': 0.41734734177589417, 'eval_rmse': 0.6460242867469788, 'eval_mae': 0.49992823600769043, 'eval_runtime': 0.3094, 'eval_samples_per_second': 222.982, 'eval_steps_per_second': 29.085, 'epoch': 47.0}
|
| 393 |
+
Saving model checkpoint to our_esol_model/checkpoint-4183
|
| 394 |
+
Configuration saved in our_esol_model/checkpoint-4183/config.json
|
| 395 |
+
Model weights saved in our_esol_model/checkpoint-4183/pytorch_model.bin
|
| 396 |
+
Deleting older checkpoint [our_esol_model/checkpoint-4094] due to args.save_total_limit
|
| 397 |
+
***** Running Evaluation *****
|
| 398 |
+
Num examples = 69
|
| 399 |
+
Batch size = 8
|
| 400 |
+
{'eval_loss': 0.41815370321273804, 'eval_mse': 0.4181537628173828, 'eval_rmse': 0.646648108959198, 'eval_mae': 0.4995117783546448, 'eval_runtime': 0.3301, 'eval_samples_per_second': 209.019, 'eval_steps_per_second': 27.263, 'epoch': 48.0}
|
| 401 |
+
Saving model checkpoint to our_esol_model/checkpoint-4272
|
| 402 |
+
Configuration saved in our_esol_model/checkpoint-4272/config.json
|
| 403 |
+
Model weights saved in our_esol_model/checkpoint-4272/pytorch_model.bin
|
| 404 |
+
Deleting older checkpoint [our_esol_model/checkpoint-4183] due to args.save_total_limit
|
| 405 |
+
***** Running Evaluation *****
|
| 406 |
+
Num examples = 69
|
| 407 |
+
Batch size = 8
|
| 408 |
+
{'eval_loss': 0.41537874937057495, 'eval_mse': 0.41537871956825256, 'eval_rmse': 0.6444988250732422, 'eval_mae': 0.49763771891593933, 'eval_runtime': 0.3396, 'eval_samples_per_second': 203.201, 'eval_steps_per_second': 26.504, 'epoch': 49.0}
|
| 409 |
+
Saving model checkpoint to our_esol_model/checkpoint-4361
|
| 410 |
+
Configuration saved in our_esol_model/checkpoint-4361/config.json
|
| 411 |
+
Model weights saved in our_esol_model/checkpoint-4361/pytorch_model.bin
|
| 412 |
+
Deleting older checkpoint [our_esol_model/checkpoint-4272] due to args.save_total_limit
|
| 413 |
+
***** Running Evaluation *****
|
| 414 |
+
Num examples = 69
|
| 415 |
+
Batch size = 8
|
| 416 |
+
{'eval_loss': 0.41592642664909363, 'eval_mse': 0.4159264862537384, 'eval_rmse': 0.6449236273765564, 'eval_mae': 0.4979737401008606, 'eval_runtime': 0.3167, 'eval_samples_per_second': 217.87, 'eval_steps_per_second': 28.418, 'epoch': 50.0}
|
| 417 |
+
Saving model checkpoint to our_esol_model/checkpoint-4450
|
| 418 |
+
Configuration saved in our_esol_model/checkpoint-4450/config.json
|
| 419 |
+
Model weights saved in our_esol_model/checkpoint-4450/pytorch_model.bin
|
| 420 |
+
Deleting older checkpoint [our_esol_model/checkpoint-4361] due to args.save_total_limit
|
| 421 |
+
|
| 422 |
+
|
| 423 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
| 424 |
+
|
| 425 |
+
|
| 426 |
+
{'train_runtime': 842.012, 'train_samples_per_second': 42.22, 'train_steps_per_second': 5.285, 'train_loss': 0.1603796991069665, 'epoch': 50.0}
|
| 427 |
+
Metrics
|
| 428 |
+
TrainOutput(global_step=4450, training_loss=0.1603796991069665, metrics={'train_runtime': 842.012, 'train_samples_per_second': 42.22, 'train_steps_per_second': 5.285, 'train_loss': 0.1603796991069665, 'epoch': 50.0})
|
| 429 |
+
Saving model checkpoint to our_esol_model
|
| 430 |
+
Configuration saved in our_esol_model/config.json
|
| 431 |
+
Model weights saved in our_esol_model/pytorch_model.bin
|
| 432 |
+
***** Running Prediction *****
|
| 433 |
+
Num examples = 84
|
| 434 |
+
Batch size = 8
|
| 435 |
+
|
| 436 |
+
Mean Squared Error (MSE): 0.4865848875608107
|
| 437 |
+
Root Mean Square Error (RMSE): 0.6975563687336033
|
| 438 |
+
Mean Absolute Error (MAE): 0.5087872081718275
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9cc2ad8d7639cc750cd8a674d0acf96eda2c3b278a93a3a842e9c199ae8c513
|
| 3 |
+
size 349077673
|
runs/Apr09_13-58-06_lotan/1649512692.4007227/events.out.tfevents.1649512692.lotan.2908091.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:453a60a1099055bd75a5c9de182344b26fb06fce9c5a2b3bd44861a5e883f151
|
| 3 |
+
size 4715
|
runs/Apr09_13-58-06_lotan/events.out.tfevents.1649512692.lotan.2908091.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5d270c06b2bb200bd21c08bc3d534eb6688719c76944f56e6926d34090e7ee3
|
| 3 |
+
size 25642
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e70d540936d1af4eab804783634188cb1039b7caf62609f969280423a545121
|
| 3 |
+
size 2927
|