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.1751389205.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": 0,
|
| 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:ccb52dec42443b04a131f8ca9c085640615f92dfcca81bd3e150958ece38b98a
|
| 3 |
+
size 891558696
|
checkpoint-23166/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f95f65f67e010abb7243112ffff75d51ff38a81f31b33429e080c9dd1b22a12
|
| 3 |
+
size 1783272762
|
checkpoint-23166/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e0cc889e9968a8f57173c2904958f82d9a7f77598a95cc243dde5d4df8c38a0
|
| 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": 0.1824825595944425,
|
| 3 |
+
"best_model_checkpoint": "./logs/mean_codet5-base_L0_codetrans_442_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": 7.1901164054870605,
|
| 14 |
+
"learning_rate": 7.77302759424796e-06,
|
| 15 |
+
"loss": 3.1407,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.777000777000777,
|
| 20 |
+
"grad_norm": 1.9955435991287231,
|
| 21 |
+
"learning_rate": 1.554605518849592e-05,
|
| 22 |
+
"loss": 0.7094,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_bleu": 0.1736803756411899,
|
| 28 |
+
"eval_brevity_penalty": 0.197226426155051,
|
| 29 |
+
"eval_length_ratio": 0.381184309616581,
|
| 30 |
+
"eval_loss": 0.37311679124832153,
|
| 31 |
+
"eval_precision": [
|
| 32 |
+
0.9371228552408358,
|
| 33 |
+
0.8909004080923851,
|
| 34 |
+
0.8609361627422151,
|
| 35 |
+
0.8366540936321278
|
| 36 |
+
],
|
| 37 |
+
"eval_reference_length": 122164,
|
| 38 |
+
"eval_rouge1": 0.542908558390936,
|
| 39 |
+
"eval_rouge2": 0.44368001967890175,
|
| 40 |
+
"eval_rougeL": 0.540620682845836,
|
| 41 |
+
"eval_rougeLsum": 0.5405855857785009,
|
| 42 |
+
"eval_runtime": 18.8167,
|
| 43 |
+
"eval_samples_per_second": 26.519,
|
| 44 |
+
"eval_steps_per_second": 1.701,
|
| 45 |
+
"eval_translation_length": 46567,
|
| 46 |
+
"step": 2574
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.1655011655011656,
|
| 50 |
+
"grad_norm": 1.8481171131134033,
|
| 51 |
+
"learning_rate": 1.9631372210471794e-05,
|
| 52 |
+
"loss": 0.4929,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.554001554001554,
|
| 57 |
+
"grad_norm": 2.2614548206329346,
|
| 58 |
+
"learning_rate": 1.8768075279492384e-05,
|
| 59 |
+
"loss": 0.3846,
|
| 60 |
+
"step": 4000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.9425019425019425,
|
| 64 |
+
"grad_norm": 2.400437593460083,
|
| 65 |
+
"learning_rate": 1.790477834851297e-05,
|
| 66 |
+
"loss": 0.3376,
|
| 67 |
+
"step": 5000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.0,
|
| 71 |
+
"eval_bleu": 0.18057798435312716,
|
| 72 |
+
"eval_brevity_penalty": 0.19824926264198342,
|
| 73 |
+
"eval_length_ratio": 0.3819373956321011,
|
| 74 |
+
"eval_loss": 0.2467917799949646,
|
| 75 |
+
"eval_precision": [
|
| 76 |
+
0.9505775948905891,
|
| 77 |
+
0.9172227036395147,
|
| 78 |
+
0.8967171108823723,
|
| 79 |
+
0.8804304503786369
|
| 80 |
+
],
|
| 81 |
+
"eval_reference_length": 122164,
|
| 82 |
+
"eval_rouge1": 0.5736859558043692,
|
| 83 |
+
"eval_rouge2": 0.49853243665675073,
|
| 84 |
+
"eval_rougeL": 0.5711789617117408,
|
| 85 |
+
"eval_rougeLsum": 0.5709334714348795,
|
| 86 |
+
"eval_runtime": 18.7791,
|
| 87 |
+
"eval_samples_per_second": 26.572,
|
| 88 |
+
"eval_steps_per_second": 1.704,
|
| 89 |
+
"eval_translation_length": 46659,
|
| 90 |
+
"step": 5148
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.331002331002331,
|
| 94 |
+
"grad_norm": 0.7062238454818726,
|
| 95 |
+
"learning_rate": 1.7041481417533562e-05,
|
| 96 |
+
"loss": 0.2698,
|
| 97 |
+
"step": 6000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.7195027195027195,
|
| 101 |
+
"grad_norm": 1.5017120838165283,
|
| 102 |
+
"learning_rate": 1.6178184486554153e-05,
|
| 103 |
+
"loss": 0.2468,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.0,
|
| 108 |
+
"eval_bleu": 0.18183623046440311,
|
| 109 |
+
"eval_brevity_penalty": 0.19878341244656408,
|
| 110 |
+
"eval_length_ratio": 0.3823303100749812,
|
| 111 |
+
"eval_loss": 0.21122430264949799,
|
| 112 |
+
"eval_precision": [
|
| 113 |
+
0.9503714646626844,
|
| 114 |
+
0.9200787742382271,
|
| 115 |
+
0.9017042595550111,
|
| 116 |
+
0.888011501880115
|
| 117 |
+
],
|
| 118 |
+
"eval_reference_length": 122164,
|
| 119 |
+
"eval_rouge1": 0.5838596613192766,
|
| 120 |
+
"eval_rouge2": 0.5170843010831574,
|
| 121 |
+
"eval_rougeL": 0.5821872231632146,
|
| 122 |
+
"eval_rougeLsum": 0.582046129578992,
|
| 123 |
+
"eval_runtime": 18.7324,
|
| 124 |
+
"eval_samples_per_second": 26.638,
|
| 125 |
+
"eval_steps_per_second": 1.708,
|
| 126 |
+
"eval_translation_length": 46707,
|
| 127 |
+
"step": 7722
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.108003108003108,
|
| 131 |
+
"grad_norm": 1.7965022325515747,
|
| 132 |
+
"learning_rate": 1.5314887555574744e-05,
|
| 133 |
+
"loss": 0.2263,
|
| 134 |
+
"step": 8000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.4965034965034967,
|
| 138 |
+
"grad_norm": 2.56624174118042,
|
| 139 |
+
"learning_rate": 1.4451590624595331e-05,
|
| 140 |
+
"loss": 0.1898,
|
| 141 |
+
"step": 9000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.885003885003885,
|
| 145 |
+
"grad_norm": 3.6289539337158203,
|
| 146 |
+
"learning_rate": 1.358829369361592e-05,
|
| 147 |
+
"loss": 0.1881,
|
| 148 |
+
"step": 10000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 4.0,
|
| 152 |
+
"eval_bleu": 0.18038030144331346,
|
| 153 |
+
"eval_brevity_penalty": 0.1935790556429139,
|
| 154 |
+
"eval_length_ratio": 0.37849120853934054,
|
| 155 |
+
"eval_loss": 0.196180060505867,
|
| 156 |
+
"eval_precision": [
|
| 157 |
+
0.9588433755785285,
|
| 158 |
+
0.9362032401233084,
|
| 159 |
+
0.9218169761273209,
|
| 160 |
+
0.9110882635613866
|
| 161 |
+
],
|
| 162 |
+
"eval_reference_length": 122164,
|
| 163 |
+
"eval_rouge1": 0.5967585694205817,
|
| 164 |
+
"eval_rouge2": 0.5331180345774978,
|
| 165 |
+
"eval_rougeL": 0.593608151081129,
|
| 166 |
+
"eval_rougeLsum": 0.5931451376073201,
|
| 167 |
+
"eval_runtime": 18.7752,
|
| 168 |
+
"eval_samples_per_second": 26.578,
|
| 169 |
+
"eval_steps_per_second": 1.704,
|
| 170 |
+
"eval_translation_length": 46238,
|
| 171 |
+
"step": 10296
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.273504273504273,
|
| 175 |
+
"grad_norm": 1.701177954673767,
|
| 176 |
+
"learning_rate": 1.272499676263651e-05,
|
| 177 |
+
"loss": 0.1563,
|
| 178 |
+
"step": 11000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.662004662004662,
|
| 182 |
+
"grad_norm": 1.5033150911331177,
|
| 183 |
+
"learning_rate": 1.1861699831657098e-05,
|
| 184 |
+
"loss": 0.1494,
|
| 185 |
+
"step": 12000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 5.0,
|
| 189 |
+
"eval_bleu": 0.1799927115538673,
|
| 190 |
+
"eval_brevity_penalty": 0.1937671187820538,
|
| 191 |
+
"eval_length_ratio": 0.3786303657378606,
|
| 192 |
+
"eval_loss": 0.18687079846858978,
|
| 193 |
+
"eval_precision": [
|
| 194 |
+
0.9576478218570965,
|
| 195 |
+
0.9330579596118542,
|
| 196 |
+
0.9182446914289503,
|
| 197 |
+
0.9074578846239778
|
| 198 |
+
],
|
| 199 |
+
"eval_reference_length": 122164,
|
| 200 |
+
"eval_rouge1": 0.5929320416450523,
|
| 201 |
+
"eval_rouge2": 0.5298831745470216,
|
| 202 |
+
"eval_rougeL": 0.591697357719601,
|
| 203 |
+
"eval_rougeLsum": 0.5909817422098348,
|
| 204 |
+
"eval_runtime": 18.8232,
|
| 205 |
+
"eval_samples_per_second": 26.51,
|
| 206 |
+
"eval_steps_per_second": 1.7,
|
| 207 |
+
"eval_translation_length": 46255,
|
| 208 |
+
"step": 12870
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 5.05050505050505,
|
| 212 |
+
"grad_norm": 1.158062219619751,
|
| 213 |
+
"learning_rate": 1.0998402900677689e-05,
|
| 214 |
+
"loss": 0.1457,
|
| 215 |
+
"step": 13000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.439005439005439,
|
| 219 |
+
"grad_norm": 2.310692071914673,
|
| 220 |
+
"learning_rate": 1.0135105969698278e-05,
|
| 221 |
+
"loss": 0.124,
|
| 222 |
+
"step": 14000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.827505827505828,
|
| 226 |
+
"grad_norm": 2.6732256412506104,
|
| 227 |
+
"learning_rate": 9.271809038718868e-06,
|
| 228 |
+
"loss": 0.1213,
|
| 229 |
+
"step": 15000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 6.0,
|
| 233 |
+
"eval_bleu": 0.18111606718257248,
|
| 234 |
+
"eval_brevity_penalty": 0.1937339279469236,
|
| 235 |
+
"eval_length_ratio": 0.37860580858518056,
|
| 236 |
+
"eval_loss": 0.18210294842720032,
|
| 237 |
+
"eval_precision": [
|
| 238 |
+
0.960390902015048,
|
| 239 |
+
0.9384521233580312,
|
| 240 |
+
0.9253104697927255,
|
| 241 |
+
0.9159200089375489
|
| 242 |
+
],
|
| 243 |
+
"eval_reference_length": 122164,
|
| 244 |
+
"eval_rouge1": 0.5996617464833769,
|
| 245 |
+
"eval_rouge2": 0.540369539631623,
|
| 246 |
+
"eval_rougeL": 0.5968260827603258,
|
| 247 |
+
"eval_rougeLsum": 0.5971458893847705,
|
| 248 |
+
"eval_runtime": 18.6822,
|
| 249 |
+
"eval_samples_per_second": 26.71,
|
| 250 |
+
"eval_steps_per_second": 1.713,
|
| 251 |
+
"eval_translation_length": 46252,
|
| 252 |
+
"step": 15444
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 6.216006216006216,
|
| 256 |
+
"grad_norm": 0.9113652110099792,
|
| 257 |
+
"learning_rate": 8.408512107739457e-06,
|
| 258 |
+
"loss": 0.1181,
|
| 259 |
+
"step": 16000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.6045066045066045,
|
| 263 |
+
"grad_norm": 1.4644179344177246,
|
| 264 |
+
"learning_rate": 7.545215176760047e-06,
|
| 265 |
+
"loss": 0.105,
|
| 266 |
+
"step": 17000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.993006993006993,
|
| 270 |
+
"grad_norm": 1.1874661445617676,
|
| 271 |
+
"learning_rate": 6.681918245780636e-06,
|
| 272 |
+
"loss": 0.1062,
|
| 273 |
+
"step": 18000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 7.0,
|
| 277 |
+
"eval_bleu": 0.1810200558437628,
|
| 278 |
+
"eval_brevity_penalty": 0.1929819734121673,
|
| 279 |
+
"eval_length_ratio": 0.3780491797911005,
|
| 280 |
+
"eval_loss": 0.1791285127401352,
|
| 281 |
+
"eval_precision": [
|
| 282 |
+
0.9621946994630175,
|
| 283 |
+
0.9416219765787458,
|
| 284 |
+
0.9289381666887974,
|
| 285 |
+
0.9198424597757737
|
| 286 |
+
],
|
| 287 |
+
"eval_reference_length": 122164,
|
| 288 |
+
"eval_rouge1": 0.6039747655980299,
|
| 289 |
+
"eval_rouge2": 0.5451908095821727,
|
| 290 |
+
"eval_rougeL": 0.6018471573861508,
|
| 291 |
+
"eval_rougeLsum": 0.6018829201876422,
|
| 292 |
+
"eval_runtime": 18.7556,
|
| 293 |
+
"eval_samples_per_second": 26.605,
|
| 294 |
+
"eval_steps_per_second": 1.706,
|
| 295 |
+
"eval_translation_length": 46184,
|
| 296 |
+
"step": 18018
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.381507381507381,
|
| 300 |
+
"grad_norm": 1.8919249773025513,
|
| 301 |
+
"learning_rate": 5.818621314801226e-06,
|
| 302 |
+
"loss": 0.0943,
|
| 303 |
+
"step": 19000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.77000777000777,
|
| 307 |
+
"grad_norm": 1.3576633930206299,
|
| 308 |
+
"learning_rate": 4.955324383821816e-06,
|
| 309 |
+
"loss": 0.0905,
|
| 310 |
+
"step": 20000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 8.0,
|
| 314 |
+
"eval_bleu": 0.18178205962569488,
|
| 315 |
+
"eval_brevity_penalty": 0.19351269101185903,
|
| 316 |
+
"eval_length_ratio": 0.37844209423398056,
|
| 317 |
+
"eval_loss": 0.17606616020202637,
|
| 318 |
+
"eval_precision": [
|
| 319 |
+
0.9616499394358886,
|
| 320 |
+
0.9426453545579778,
|
| 321 |
+
0.9310474421895034,
|
| 322 |
+
0.9226332848999664
|
| 323 |
+
],
|
| 324 |
+
"eval_reference_length": 122164,
|
| 325 |
+
"eval_rouge1": 0.6034570691611103,
|
| 326 |
+
"eval_rouge2": 0.5459492490530148,
|
| 327 |
+
"eval_rougeL": 0.6018724893326528,
|
| 328 |
+
"eval_rougeLsum": 0.6009358596439488,
|
| 329 |
+
"eval_runtime": 18.6897,
|
| 330 |
+
"eval_samples_per_second": 26.699,
|
| 331 |
+
"eval_steps_per_second": 1.712,
|
| 332 |
+
"eval_translation_length": 46232,
|
| 333 |
+
"step": 20592
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 8.158508158508159,
|
| 337 |
+
"grad_norm": 1.9662929773330688,
|
| 338 |
+
"learning_rate": 4.092027452842406e-06,
|
| 339 |
+
"loss": 0.0855,
|
| 340 |
+
"step": 21000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 8.547008547008547,
|
| 344 |
+
"grad_norm": 1.0135780572891235,
|
| 345 |
+
"learning_rate": 3.228730521862995e-06,
|
| 346 |
+
"loss": 0.084,
|
| 347 |
+
"step": 22000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 8.935508935508935,
|
| 351 |
+
"grad_norm": 1.0170562267303467,
|
| 352 |
+
"learning_rate": 2.3654335908835845e-06,
|
| 353 |
+
"loss": 0.0784,
|
| 354 |
+
"step": 23000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 9.0,
|
| 358 |
+
"eval_bleu": 0.1824825595944425,
|
| 359 |
+
"eval_brevity_penalty": 0.19489642572236812,
|
| 360 |
+
"eval_length_ratio": 0.3794653089289807,
|
| 361 |
+
"eval_loss": 0.175808846950531,
|
| 362 |
+
"eval_precision": [
|
| 363 |
+
0.9595098906314041,
|
| 364 |
+
0.9397487897422478,
|
| 365 |
+
0.9276659538349611,
|
| 366 |
+
0.9187917967008471
|
| 367 |
+
],
|
| 368 |
+
"eval_reference_length": 122164,
|
| 369 |
+
"eval_rouge1": 0.6016816992206656,
|
| 370 |
+
"eval_rouge2": 0.5439470969941985,
|
| 371 |
+
"eval_rougeL": 0.6002099939977966,
|
| 372 |
+
"eval_rougeLsum": 0.600075041296938,
|
| 373 |
+
"eval_runtime": 18.6701,
|
| 374 |
+
"eval_samples_per_second": 26.727,
|
| 375 |
+
"eval_steps_per_second": 1.714,
|
| 376 |
+
"eval_translation_length": 46357,
|
| 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:a217b31b130f40bd8342c3b9b32b417b1a151233b2952470db15e70be0cc574b
|
| 3 |
+
size 5496
|
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": 0,
|
| 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.1751389205.gra5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:740d19c27ad5c8d5bbabdeedf9a55b7b1044f191df6e451181d592b1f3883fff
|
| 3 |
+
size 19660
|
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:ccb52dec42443b04a131f8ca9c085640615f92dfcca81bd3e150958ece38b98a
|
| 3 |
+
size 891558696
|
results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"rouge1": 0.7640239998010208,
|
| 3 |
+
"rouge2": 0.7085748694600479,
|
| 4 |
+
"rougeL": 0.7617181227380305,
|
| 5 |
+
"rougeLsum": 0.7612436205055559,
|
| 6 |
+
"bleu": 0.6821600881694196,
|
| 7 |
+
"precision": [
|
| 8 |
+
0.7059251710583783,
|
| 9 |
+
0.6852724351851264,
|
| 10 |
+
0.673469777752298,
|
| 11 |
+
0.664668630621074
|
| 12 |
+
],
|
| 13 |
+
"brevity_penalty": 1.0,
|
| 14 |
+
"length_ratio": 1.3877072399481762,
|
| 15 |
+
"translation_length": 315974,
|
| 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:a217b31b130f40bd8342c3b9b32b417b1a151233b2952470db15e70be0cc574b
|
| 3 |
+
size 5496
|