Upload folder using huggingface_hub
Browse files- checkpoint-23166/config.json +71 -0
- checkpoint-23166/generation_config.json +7 -0
- checkpoint-23166/model.safetensors +3 -0
- checkpoint-23166/optimizer.pt +3 -0
- checkpoint-23166/rng_state.pth +3 -0
- checkpoint-23166/scheduler.pt +3 -0
- checkpoint-23166/trainer_state.json +401 -0
- checkpoint-23166/training_args.bin +3 -0
- config.json +71 -0
- events.out.tfevents.1751348775.gra5 +3 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- results.json +17 -0
- training_args.bin +3 -0
checkpoint-23166/config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/mootez/projects/def-tusharma/mootez/local_models/codet5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 3072,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 0,
|
| 12 |
+
"dense_act_fn": "relu",
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"feed_forward_proj": "relu",
|
| 16 |
+
"gradient_checkpointing": false,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "LABEL_0"
|
| 19 |
+
},
|
| 20 |
+
"initializer_factor": 1.0,
|
| 21 |
+
"is_encoder_decoder": true,
|
| 22 |
+
"is_gated_act": false,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_epsilon": 1e-06,
|
| 27 |
+
"merge_layer_index": 3,
|
| 28 |
+
"merger_type": "mean",
|
| 29 |
+
"model_type": "t5",
|
| 30 |
+
"n_positions": 512,
|
| 31 |
+
"num_decoder_layers": 12,
|
| 32 |
+
"num_heads": 12,
|
| 33 |
+
"num_layers": 12,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"relative_attention_max_distance": 128,
|
| 37 |
+
"relative_attention_num_buckets": 32,
|
| 38 |
+
"task_specific_params": {
|
| 39 |
+
"summarization": {
|
| 40 |
+
"early_stopping": true,
|
| 41 |
+
"length_penalty": 2.0,
|
| 42 |
+
"max_length": 200,
|
| 43 |
+
"min_length": 30,
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"num_beams": 4,
|
| 46 |
+
"prefix": "summarize: "
|
| 47 |
+
},
|
| 48 |
+
"translation_en_to_de": {
|
| 49 |
+
"early_stopping": true,
|
| 50 |
+
"max_length": 300,
|
| 51 |
+
"num_beams": 4,
|
| 52 |
+
"prefix": "translate English to German: "
|
| 53 |
+
},
|
| 54 |
+
"translation_en_to_fr": {
|
| 55 |
+
"early_stopping": true,
|
| 56 |
+
"max_length": 300,
|
| 57 |
+
"num_beams": 4,
|
| 58 |
+
"prefix": "translate English to French: "
|
| 59 |
+
},
|
| 60 |
+
"translation_en_to_ro": {
|
| 61 |
+
"early_stopping": true,
|
| 62 |
+
"max_length": 300,
|
| 63 |
+
"num_beams": 4,
|
| 64 |
+
"prefix": "translate English to Romanian: "
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.48.2",
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"vocab_size": 32100
|
| 71 |
+
}
|
checkpoint-23166/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.48.2"
|
| 7 |
+
}
|
checkpoint-23166/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:294a9d4b57774e90930d30720f2e3d211d5be31017f131702a691262fe9591f3
|
| 3 |
+
size 891558696
|
checkpoint-23166/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76d5b8f5fde61525b26f56a081288e7230166e7ea67241a8a37f456fbdc7709f
|
| 3 |
+
size 1783272762
|
checkpoint-23166/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da6d5b789801a4fd383b5e1cb4b13fcbb80116a09f1ee1aa6e00c44669c5020e
|
| 3 |
+
size 14308
|
checkpoint-23166/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2c2312e10deee78d4bb435a96e2b6836dac000cf0e6c7350185e898e3ae8f27
|
| 3 |
+
size 1064
|
checkpoint-23166/trainer_state.json
ADDED
|
@@ -0,0 +1,401 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18306560530377253,
|
| 3 |
+
"best_model_checkpoint": "./logs/mean_codet5-base_L3_codetrans_123456_src_java_tgt_c_sharp/checkpoint-23166",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 23166,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3885003885003885,
|
| 13 |
+
"grad_norm": 4.433056354522705,
|
| 14 |
+
"learning_rate": 7.77302759424796e-06,
|
| 15 |
+
"loss": 2.912,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.777000777000777,
|
| 20 |
+
"grad_norm": 4.406907081604004,
|
| 21 |
+
"learning_rate": 1.554605518849592e-05,
|
| 22 |
+
"loss": 0.6505,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_bleu": 0.1802541174643684,
|
| 28 |
+
"eval_brevity_penalty": 0.20359458485790227,
|
| 29 |
+
"eval_length_ratio": 0.38585835434334176,
|
| 30 |
+
"eval_loss": 0.34058618545532227,
|
| 31 |
+
"eval_precision": [
|
| 32 |
+
0.9383512240655097,
|
| 33 |
+
0.8944874461287764,
|
| 34 |
+
0.8664716081491114,
|
| 35 |
+
0.8448544072215771
|
| 36 |
+
],
|
| 37 |
+
"eval_reference_length": 122164,
|
| 38 |
+
"eval_rouge1": 0.5502698056958817,
|
| 39 |
+
"eval_rouge2": 0.46174024138426223,
|
| 40 |
+
"eval_rougeL": 0.5486260876367255,
|
| 41 |
+
"eval_rougeLsum": 0.5484786029602634,
|
| 42 |
+
"eval_runtime": 18.9552,
|
| 43 |
+
"eval_samples_per_second": 26.325,
|
| 44 |
+
"eval_steps_per_second": 1.688,
|
| 45 |
+
"eval_translation_length": 47138,
|
| 46 |
+
"step": 2574
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.1655011655011656,
|
| 50 |
+
"grad_norm": 3.9919793605804443,
|
| 51 |
+
"learning_rate": 1.9631372210471794e-05,
|
| 52 |
+
"loss": 0.4334,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.554001554001554,
|
| 57 |
+
"grad_norm": 2.050812005996704,
|
| 58 |
+
"learning_rate": 1.8768075279492384e-05,
|
| 59 |
+
"loss": 0.3334,
|
| 60 |
+
"step": 4000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.9425019425019425,
|
| 64 |
+
"grad_norm": 2.9300739765167236,
|
| 65 |
+
"learning_rate": 1.790477834851297e-05,
|
| 66 |
+
"loss": 0.3061,
|
| 67 |
+
"step": 5000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.0,
|
| 71 |
+
"eval_bleu": 0.18083700336419095,
|
| 72 |
+
"eval_brevity_penalty": 0.19700423659818384,
|
| 73 |
+
"eval_length_ratio": 0.38102059526538096,
|
| 74 |
+
"eval_loss": 0.23390793800354004,
|
| 75 |
+
"eval_precision": [
|
| 76 |
+
0.9533804541646078,
|
| 77 |
+
0.9237317581653927,
|
| 78 |
+
0.9050473116863158,
|
| 79 |
+
0.8907658157602664
|
| 80 |
+
],
|
| 81 |
+
"eval_reference_length": 122164,
|
| 82 |
+
"eval_rouge1": 0.5843084940540437,
|
| 83 |
+
"eval_rouge2": 0.5147318317407648,
|
| 84 |
+
"eval_rougeL": 0.5829957165468347,
|
| 85 |
+
"eval_rougeLsum": 0.5828822765697064,
|
| 86 |
+
"eval_runtime": 18.8788,
|
| 87 |
+
"eval_samples_per_second": 26.432,
|
| 88 |
+
"eval_steps_per_second": 1.695,
|
| 89 |
+
"eval_translation_length": 46547,
|
| 90 |
+
"step": 5148
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.331002331002331,
|
| 94 |
+
"grad_norm": 4.110734462738037,
|
| 95 |
+
"learning_rate": 1.7041481417533562e-05,
|
| 96 |
+
"loss": 0.2349,
|
| 97 |
+
"step": 6000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.7195027195027195,
|
| 101 |
+
"grad_norm": 2.434936285018921,
|
| 102 |
+
"learning_rate": 1.6178184486554153e-05,
|
| 103 |
+
"loss": 0.2244,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.0,
|
| 108 |
+
"eval_bleu": 0.1802110003560423,
|
| 109 |
+
"eval_brevity_penalty": 0.1940326951134667,
|
| 110 |
+
"eval_length_ratio": 0.3788268229593006,
|
| 111 |
+
"eval_loss": 0.20088019967079163,
|
| 112 |
+
"eval_precision": [
|
| 113 |
+
0.9591175263078286,
|
| 114 |
+
0.9335517693315858,
|
| 115 |
+
0.9177800843620945,
|
| 116 |
+
0.9054754142289313
|
| 117 |
+
],
|
| 118 |
+
"eval_reference_length": 122164,
|
| 119 |
+
"eval_rouge1": 0.5911955078072093,
|
| 120 |
+
"eval_rouge2": 0.524989920894315,
|
| 121 |
+
"eval_rougeL": 0.5882527047440294,
|
| 122 |
+
"eval_rougeLsum": 0.5884088907328999,
|
| 123 |
+
"eval_runtime": 18.8747,
|
| 124 |
+
"eval_samples_per_second": 26.438,
|
| 125 |
+
"eval_steps_per_second": 1.695,
|
| 126 |
+
"eval_translation_length": 46279,
|
| 127 |
+
"step": 7722
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.108003108003108,
|
| 131 |
+
"grad_norm": 0.7912299036979675,
|
| 132 |
+
"learning_rate": 1.5314887555574744e-05,
|
| 133 |
+
"loss": 0.2021,
|
| 134 |
+
"step": 8000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.4965034965034967,
|
| 138 |
+
"grad_norm": 1.0203369855880737,
|
| 139 |
+
"learning_rate": 1.4451590624595331e-05,
|
| 140 |
+
"loss": 0.1649,
|
| 141 |
+
"step": 9000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.885003885003885,
|
| 145 |
+
"grad_norm": 0.7620385885238647,
|
| 146 |
+
"learning_rate": 1.358829369361592e-05,
|
| 147 |
+
"loss": 0.1673,
|
| 148 |
+
"step": 10000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.0,
|
| 152 |
+
"eval_bleu": 0.17893771584583518,
|
| 153 |
+
"eval_brevity_penalty": 0.1895410540683385,
|
| 154 |
+
"eval_length_ratio": 0.3754952359123801,
|
| 155 |
+
"eval_loss": 0.18250109255313873,
|
| 156 |
+
"eval_precision": [
|
| 157 |
+
0.9703740844087897,
|
| 158 |
+
0.9479646485795518,
|
| 159 |
+
0.9341266657752819,
|
| 160 |
+
0.9243943661971831
|
| 161 |
+
],
|
| 162 |
+
"eval_reference_length": 122164,
|
| 163 |
+
"eval_rouge1": 0.6074689594932872,
|
| 164 |
+
"eval_rouge2": 0.5468729759109237,
|
| 165 |
+
"eval_rougeL": 0.6056443214236831,
|
| 166 |
+
"eval_rougeLsum": 0.6053028648471293,
|
| 167 |
+
"eval_runtime": 18.8181,
|
| 168 |
+
"eval_samples_per_second": 26.517,
|
| 169 |
+
"eval_steps_per_second": 1.7,
|
| 170 |
+
"eval_translation_length": 45872,
|
| 171 |
+
"step": 10296
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.273504273504273,
|
| 175 |
+
"grad_norm": 0.4687822163105011,
|
| 176 |
+
"learning_rate": 1.272499676263651e-05,
|
| 177 |
+
"loss": 0.1439,
|
| 178 |
+
"step": 11000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.662004662004662,
|
| 182 |
+
"grad_norm": 1.5569430589675903,
|
| 183 |
+
"learning_rate": 1.1861699831657098e-05,
|
| 184 |
+
"loss": 0.1364,
|
| 185 |
+
"step": 12000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 5.0,
|
| 189 |
+
"eval_bleu": 0.1829934347882755,
|
| 190 |
+
"eval_brevity_penalty": 0.19598293429482344,
|
| 191 |
+
"eval_length_ratio": 0.38026750924986086,
|
| 192 |
+
"eval_loss": 0.17416685819625854,
|
| 193 |
+
"eval_precision": [
|
| 194 |
+
0.9583898396297492,
|
| 195 |
+
0.9370702411001828,
|
| 196 |
+
0.9244560793717139,
|
| 197 |
+
0.9155211530762044
|
| 198 |
+
],
|
| 199 |
+
"eval_reference_length": 122164,
|
| 200 |
+
"eval_rouge1": 0.6000262882981056,
|
| 201 |
+
"eval_rouge2": 0.5415090121281508,
|
| 202 |
+
"eval_rougeL": 0.597907843569306,
|
| 203 |
+
"eval_rougeLsum": 0.5982219703594538,
|
| 204 |
+
"eval_runtime": 18.8209,
|
| 205 |
+
"eval_samples_per_second": 26.513,
|
| 206 |
+
"eval_steps_per_second": 1.7,
|
| 207 |
+
"eval_translation_length": 46455,
|
| 208 |
+
"step": 12870
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 5.05050505050505,
|
| 212 |
+
"grad_norm": 1.3390740156173706,
|
| 213 |
+
"learning_rate": 1.0998402900677689e-05,
|
| 214 |
+
"loss": 0.1308,
|
| 215 |
+
"step": 13000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.439005439005439,
|
| 219 |
+
"grad_norm": 0.5635651350021362,
|
| 220 |
+
"learning_rate": 1.0135105969698278e-05,
|
| 221 |
+
"loss": 0.1107,
|
| 222 |
+
"step": 14000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.827505827505828,
|
| 226 |
+
"grad_norm": 0.7251797318458557,
|
| 227 |
+
"learning_rate": 9.271809038718868e-06,
|
| 228 |
+
"loss": 0.1137,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 6.0,
|
| 233 |
+
"eval_bleu": 0.18253678525787156,
|
| 234 |
+
"eval_brevity_penalty": 0.19550602228730055,
|
| 235 |
+
"eval_length_ratio": 0.3799155233947808,
|
| 236 |
+
"eval_loss": 0.17129658162593842,
|
| 237 |
+
"eval_precision": [
|
| 238 |
+
0.958265103852452,
|
| 239 |
+
0.9372726678718446,
|
| 240 |
+
0.9243184920949487,
|
| 241 |
+
0.9153512189691639
|
| 242 |
+
],
|
| 243 |
+
"eval_reference_length": 122164,
|
| 244 |
+
"eval_rouge1": 0.5988787490336176,
|
| 245 |
+
"eval_rouge2": 0.5410338967122212,
|
| 246 |
+
"eval_rougeL": 0.5978781596632818,
|
| 247 |
+
"eval_rougeLsum": 0.5977930629700651,
|
| 248 |
+
"eval_runtime": 18.88,
|
| 249 |
+
"eval_samples_per_second": 26.43,
|
| 250 |
+
"eval_steps_per_second": 1.695,
|
| 251 |
+
"eval_translation_length": 46412,
|
| 252 |
+
"step": 15444
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 6.216006216006216,
|
| 256 |
+
"grad_norm": 0.4674796760082245,
|
| 257 |
+
"learning_rate": 8.408512107739457e-06,
|
| 258 |
+
"loss": 0.0988,
|
| 259 |
+
"step": 16000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.6045066045066045,
|
| 263 |
+
"grad_norm": 1.7097464799880981,
|
| 264 |
+
"learning_rate": 7.545215176760047e-06,
|
| 265 |
+
"loss": 0.0958,
|
| 266 |
+
"step": 17000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.993006993006993,
|
| 270 |
+
"grad_norm": 0.4805188477039337,
|
| 271 |
+
"learning_rate": 6.681918245780636e-06,
|
| 272 |
+
"loss": 0.0941,
|
| 273 |
+
"step": 18000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 7.0,
|
| 277 |
+
"eval_bleu": 0.18135626584871561,
|
| 278 |
+
"eval_brevity_penalty": 0.19265045545778284,
|
| 279 |
+
"eval_length_ratio": 0.37780360826430043,
|
| 280 |
+
"eval_loss": 0.16954277455806732,
|
| 281 |
+
"eval_precision": [
|
| 282 |
+
0.9642501191662695,
|
| 283 |
+
0.9447596101193736,
|
| 284 |
+
0.932744264328107,
|
| 285 |
+
0.924222406341671
|
| 286 |
+
],
|
| 287 |
+
"eval_reference_length": 122164,
|
| 288 |
+
"eval_rouge1": 0.6038418385279647,
|
| 289 |
+
"eval_rouge2": 0.5472933346770577,
|
| 290 |
+
"eval_rougeL": 0.602328618074782,
|
| 291 |
+
"eval_rougeLsum": 0.6020615566143752,
|
| 292 |
+
"eval_runtime": 18.9027,
|
| 293 |
+
"eval_samples_per_second": 26.398,
|
| 294 |
+
"eval_steps_per_second": 1.693,
|
| 295 |
+
"eval_translation_length": 46154,
|
| 296 |
+
"step": 18018
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.381507381507381,
|
| 300 |
+
"grad_norm": 1.1238845586776733,
|
| 301 |
+
"learning_rate": 5.818621314801226e-06,
|
| 302 |
+
"loss": 0.085,
|
| 303 |
+
"step": 19000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.77000777000777,
|
| 307 |
+
"grad_norm": 0.8810899257659912,
|
| 308 |
+
"learning_rate": 4.955324383821816e-06,
|
| 309 |
+
"loss": 0.077,
|
| 310 |
+
"step": 20000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.0,
|
| 314 |
+
"eval_bleu": 0.18135849831407855,
|
| 315 |
+
"eval_brevity_penalty": 0.19214239874241087,
|
| 316 |
+
"eval_length_ratio": 0.3774270652565404,
|
| 317 |
+
"eval_loss": 0.16934679448604584,
|
| 318 |
+
"eval_precision": [
|
| 319 |
+
0.9651470460657586,
|
| 320 |
+
0.9468964458769102,
|
| 321 |
+
0.9358235424517846,
|
| 322 |
+
0.9280446526641412
|
| 323 |
+
],
|
| 324 |
+
"eval_reference_length": 122164,
|
| 325 |
+
"eval_rouge1": 0.6055629252789044,
|
| 326 |
+
"eval_rouge2": 0.5518668287474647,
|
| 327 |
+
"eval_rougeL": 0.6041993482805612,
|
| 328 |
+
"eval_rougeLsum": 0.6042497461553049,
|
| 329 |
+
"eval_runtime": 18.7961,
|
| 330 |
+
"eval_samples_per_second": 26.548,
|
| 331 |
+
"eval_steps_per_second": 1.702,
|
| 332 |
+
"eval_translation_length": 46108,
|
| 333 |
+
"step": 20592
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 8.158508158508159,
|
| 337 |
+
"grad_norm": 1.9647403955459595,
|
| 338 |
+
"learning_rate": 4.092027452842406e-06,
|
| 339 |
+
"loss": 0.078,
|
| 340 |
+
"step": 21000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 8.547008547008547,
|
| 344 |
+
"grad_norm": 0.9425419569015503,
|
| 345 |
+
"learning_rate": 3.228730521862995e-06,
|
| 346 |
+
"loss": 0.072,
|
| 347 |
+
"step": 22000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 8.935508935508935,
|
| 351 |
+
"grad_norm": 1.0749077796936035,
|
| 352 |
+
"learning_rate": 2.3654335908835845e-06,
|
| 353 |
+
"loss": 0.072,
|
| 354 |
+
"step": 23000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 9.0,
|
| 358 |
+
"eval_bleu": 0.18306560530377253,
|
| 359 |
+
"eval_brevity_penalty": 0.19502938952101778,
|
| 360 |
+
"eval_length_ratio": 0.37956353753970073,
|
| 361 |
+
"eval_loss": 0.16787013411521912,
|
| 362 |
+
"eval_precision": [
|
| 363 |
+
0.9598654273329164,
|
| 364 |
+
0.9416394157401352,
|
| 365 |
+
0.9306385135879747,
|
| 366 |
+
0.9228917810661437
|
| 367 |
+
],
|
| 368 |
+
"eval_reference_length": 122164,
|
| 369 |
+
"eval_rouge1": 0.6031676081849873,
|
| 370 |
+
"eval_rouge2": 0.5479430822848634,
|
| 371 |
+
"eval_rougeL": 0.6014386050547871,
|
| 372 |
+
"eval_rougeLsum": 0.6018104865518734,
|
| 373 |
+
"eval_runtime": 18.8066,
|
| 374 |
+
"eval_samples_per_second": 26.533,
|
| 375 |
+
"eval_steps_per_second": 1.702,
|
| 376 |
+
"eval_translation_length": 46369,
|
| 377 |
+
"step": 23166
|
| 378 |
+
}
|
| 379 |
+
],
|
| 380 |
+
"logging_steps": 1000,
|
| 381 |
+
"max_steps": 25740,
|
| 382 |
+
"num_input_tokens_seen": 0,
|
| 383 |
+
"num_train_epochs": 10,
|
| 384 |
+
"save_steps": 500,
|
| 385 |
+
"stateful_callbacks": {
|
| 386 |
+
"TrainerControl": {
|
| 387 |
+
"args": {
|
| 388 |
+
"should_epoch_stop": false,
|
| 389 |
+
"should_evaluate": false,
|
| 390 |
+
"should_log": false,
|
| 391 |
+
"should_save": true,
|
| 392 |
+
"should_training_stop": false
|
| 393 |
+
},
|
| 394 |
+
"attributes": {}
|
| 395 |
+
}
|
| 396 |
+
},
|
| 397 |
+
"total_flos": 2.8101295516032e+16,
|
| 398 |
+
"train_batch_size": 4,
|
| 399 |
+
"trial_name": null,
|
| 400 |
+
"trial_params": null
|
| 401 |
+
}
|
checkpoint-23166/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27437889e5e27e95152290950b09bc25f54fe3777f781b6bbe6c766365332668
|
| 3 |
+
size 5560
|
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/mootez/projects/def-tusharma/mootez/local_models/codet5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 3072,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 0,
|
| 12 |
+
"dense_act_fn": "relu",
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"feed_forward_proj": "relu",
|
| 16 |
+
"gradient_checkpointing": false,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "LABEL_0"
|
| 19 |
+
},
|
| 20 |
+
"initializer_factor": 1.0,
|
| 21 |
+
"is_encoder_decoder": true,
|
| 22 |
+
"is_gated_act": false,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_epsilon": 1e-06,
|
| 27 |
+
"merge_layer_index": 3,
|
| 28 |
+
"merger_type": "mean",
|
| 29 |
+
"model_type": "t5",
|
| 30 |
+
"n_positions": 512,
|
| 31 |
+
"num_decoder_layers": 12,
|
| 32 |
+
"num_heads": 12,
|
| 33 |
+
"num_layers": 12,
|
| 34 |
+
"output_past": true,
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"relative_attention_max_distance": 128,
|
| 37 |
+
"relative_attention_num_buckets": 32,
|
| 38 |
+
"task_specific_params": {
|
| 39 |
+
"summarization": {
|
| 40 |
+
"early_stopping": true,
|
| 41 |
+
"length_penalty": 2.0,
|
| 42 |
+
"max_length": 200,
|
| 43 |
+
"min_length": 30,
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"num_beams": 4,
|
| 46 |
+
"prefix": "summarize: "
|
| 47 |
+
},
|
| 48 |
+
"translation_en_to_de": {
|
| 49 |
+
"early_stopping": true,
|
| 50 |
+
"max_length": 300,
|
| 51 |
+
"num_beams": 4,
|
| 52 |
+
"prefix": "translate English to German: "
|
| 53 |
+
},
|
| 54 |
+
"translation_en_to_fr": {
|
| 55 |
+
"early_stopping": true,
|
| 56 |
+
"max_length": 300,
|
| 57 |
+
"num_beams": 4,
|
| 58 |
+
"prefix": "translate English to French: "
|
| 59 |
+
},
|
| 60 |
+
"translation_en_to_ro": {
|
| 61 |
+
"early_stopping": true,
|
| 62 |
+
"max_length": 300,
|
| 63 |
+
"num_beams": 4,
|
| 64 |
+
"prefix": "translate English to Romanian: "
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.48.2",
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"vocab_size": 32100
|
| 71 |
+
}
|
events.out.tfevents.1751348775.gra5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e777f5df6a47087c8ad7b6d45dda518edcda1c88c9d23d279e8ea2b302b9d1e
|
| 3 |
+
size 19672
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.48.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:294a9d4b57774e90930d30720f2e3d211d5be31017f131702a691262fe9591f3
|
| 3 |
+
size 891558696
|
results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"rouge1": 0.7290724828355708,
|
| 3 |
+
"rouge2": 0.6797439550568423,
|
| 4 |
+
"rougeL": 0.7264404158196711,
|
| 5 |
+
"rougeLsum": 0.7260718022029558,
|
| 6 |
+
"bleu": 0.6177175096041058,
|
| 7 |
+
"precision": [
|
| 8 |
+
0.6378331919834705,
|
| 9 |
+
0.6202457944938837,
|
| 10 |
+
0.6102944122916989,
|
| 11 |
+
0.6030444292628038
|
| 12 |
+
],
|
| 13 |
+
"brevity_penalty": 1.0,
|
| 14 |
+
"length_ratio": 1.5431783745800303,
|
| 15 |
+
"translation_length": 351374,
|
| 16 |
+
"reference_length": 227695
|
| 17 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27437889e5e27e95152290950b09bc25f54fe3777f781b6bbe6c766365332668
|
| 3 |
+
size 5560
|