Upload 8 files
Browse files- config.json +61 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +486 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 6,
|
| 22 |
+
"num_heads": 8,
|
| 23 |
+
"num_layers": 6,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.47.0",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32128
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.47.0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad1fe52231064218954f8d595a6069dd3da00e440899a1fe60f27c71b453903
|
| 3 |
+
size 242041896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d566554b98a7eba625535be318a80f8c40700fec49835d598fd21790f9bc8a5
|
| 3 |
+
size 484163514
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a14c43825f7dcaf77362dc0679256a705cc528fcca4ed917898d35fb355d94
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f42e283fe8c01b5d3acb5a19d1221a229901bf4a89a3753e119b003cd2abcb60
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,486 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7763074636459351,
|
| 3 |
+
"best_model_checkpoint": "./t5_finetuned/checkpoint-24000",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 25622,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.019514479743970026,
|
| 13 |
+
"grad_norm": 50375.1171875,
|
| 14 |
+
"learning_rate": 3.9219420810241204e-05,
|
| 15 |
+
"loss": 1.6162,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03902895948794005,
|
| 20 |
+
"grad_norm": 40185.09765625,
|
| 21 |
+
"learning_rate": 3.84388416204824e-05,
|
| 22 |
+
"loss": 1.0952,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05854343923191008,
|
| 27 |
+
"grad_norm": 26678.357421875,
|
| 28 |
+
"learning_rate": 3.76582624307236e-05,
|
| 29 |
+
"loss": 1.0438,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0780579189758801,
|
| 34 |
+
"grad_norm": 75600.265625,
|
| 35 |
+
"learning_rate": 3.68776832409648e-05,
|
| 36 |
+
"loss": 1.0177,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0780579189758801,
|
| 41 |
+
"eval_loss": 0.9050301909446716,
|
| 42 |
+
"eval_runtime": 247.5245,
|
| 43 |
+
"eval_samples_per_second": 87.171,
|
| 44 |
+
"eval_steps_per_second": 5.45,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09757239871985013,
|
| 49 |
+
"grad_norm": 48858.64453125,
|
| 50 |
+
"learning_rate": 3.6097104051205996e-05,
|
| 51 |
+
"loss": 0.994,
|
| 52 |
+
"step": 2500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.11708687846382015,
|
| 56 |
+
"grad_norm": 38273.890625,
|
| 57 |
+
"learning_rate": 3.53165248614472e-05,
|
| 58 |
+
"loss": 0.9774,
|
| 59 |
+
"step": 3000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13660135820779018,
|
| 63 |
+
"grad_norm": 33092.80078125,
|
| 64 |
+
"learning_rate": 3.45359456716884e-05,
|
| 65 |
+
"loss": 0.9659,
|
| 66 |
+
"step": 3500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1561158379517602,
|
| 70 |
+
"grad_norm": 42197.96484375,
|
| 71 |
+
"learning_rate": 3.375536648192959e-05,
|
| 72 |
+
"loss": 0.9396,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1561158379517602,
|
| 77 |
+
"eval_loss": 0.8554931879043579,
|
| 78 |
+
"eval_runtime": 246.9587,
|
| 79 |
+
"eval_samples_per_second": 87.371,
|
| 80 |
+
"eval_steps_per_second": 5.462,
|
| 81 |
+
"step": 4000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.17563031769573023,
|
| 85 |
+
"grad_norm": 31069.32421875,
|
| 86 |
+
"learning_rate": 3.2974787292170794e-05,
|
| 87 |
+
"loss": 0.9339,
|
| 88 |
+
"step": 4500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.19514479743970026,
|
| 92 |
+
"grad_norm": 40504.2109375,
|
| 93 |
+
"learning_rate": 3.2194208102411995e-05,
|
| 94 |
+
"loss": 0.9271,
|
| 95 |
+
"step": 5000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.21465927718367028,
|
| 99 |
+
"grad_norm": 53872.625,
|
| 100 |
+
"learning_rate": 3.141362891265319e-05,
|
| 101 |
+
"loss": 0.9036,
|
| 102 |
+
"step": 5500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.2341737569276403,
|
| 106 |
+
"grad_norm": 40223.39453125,
|
| 107 |
+
"learning_rate": 3.063304972289439e-05,
|
| 108 |
+
"loss": 0.8948,
|
| 109 |
+
"step": 6000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2341737569276403,
|
| 113 |
+
"eval_loss": 0.8311675190925598,
|
| 114 |
+
"eval_runtime": 247.1162,
|
| 115 |
+
"eval_samples_per_second": 87.315,
|
| 116 |
+
"eval_steps_per_second": 5.459,
|
| 117 |
+
"step": 6000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.25368823667161033,
|
| 121 |
+
"grad_norm": 37229.52734375,
|
| 122 |
+
"learning_rate": 2.985247053313559e-05,
|
| 123 |
+
"loss": 0.9039,
|
| 124 |
+
"step": 6500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.27320271641558036,
|
| 128 |
+
"grad_norm": 42615.79296875,
|
| 129 |
+
"learning_rate": 2.9071891343376786e-05,
|
| 130 |
+
"loss": 0.9099,
|
| 131 |
+
"step": 7000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.2927171961595504,
|
| 135 |
+
"grad_norm": 45535.15234375,
|
| 136 |
+
"learning_rate": 2.8291312153617988e-05,
|
| 137 |
+
"loss": 0.9024,
|
| 138 |
+
"step": 7500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.3122316759035204,
|
| 142 |
+
"grad_norm": 44434.55078125,
|
| 143 |
+
"learning_rate": 2.7510732963859185e-05,
|
| 144 |
+
"loss": 0.9221,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.3122316759035204,
|
| 149 |
+
"eval_loss": 0.8146435618400574,
|
| 150 |
+
"eval_runtime": 247.4985,
|
| 151 |
+
"eval_samples_per_second": 87.18,
|
| 152 |
+
"eval_steps_per_second": 5.451,
|
| 153 |
+
"step": 8000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.33174615564749044,
|
| 157 |
+
"grad_norm": 106098.890625,
|
| 158 |
+
"learning_rate": 2.6730153774100383e-05,
|
| 159 |
+
"loss": 0.8931,
|
| 160 |
+
"step": 8500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.35126063539146046,
|
| 164 |
+
"grad_norm": 29800.005859375,
|
| 165 |
+
"learning_rate": 2.5949574584341584e-05,
|
| 166 |
+
"loss": 0.8991,
|
| 167 |
+
"step": 9000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.3707751151354305,
|
| 171 |
+
"grad_norm": 41034.53125,
|
| 172 |
+
"learning_rate": 2.5168995394582782e-05,
|
| 173 |
+
"loss": 0.8879,
|
| 174 |
+
"step": 9500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.3902895948794005,
|
| 178 |
+
"grad_norm": 36309.5625,
|
| 179 |
+
"learning_rate": 2.438841620482398e-05,
|
| 180 |
+
"loss": 0.873,
|
| 181 |
+
"step": 10000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.3902895948794005,
|
| 185 |
+
"eval_loss": 0.8043464422225952,
|
| 186 |
+
"eval_runtime": 247.5255,
|
| 187 |
+
"eval_samples_per_second": 87.171,
|
| 188 |
+
"eval_steps_per_second": 5.45,
|
| 189 |
+
"step": 10000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.40980407462337054,
|
| 193 |
+
"grad_norm": 28724.736328125,
|
| 194 |
+
"learning_rate": 2.360783701506518e-05,
|
| 195 |
+
"loss": 0.8964,
|
| 196 |
+
"step": 10500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.42931855436734057,
|
| 200 |
+
"grad_norm": 32160.0625,
|
| 201 |
+
"learning_rate": 2.282725782530638e-05,
|
| 202 |
+
"loss": 0.8837,
|
| 203 |
+
"step": 11000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.4488330341113106,
|
| 207 |
+
"grad_norm": 33788.734375,
|
| 208 |
+
"learning_rate": 2.2046678635547577e-05,
|
| 209 |
+
"loss": 0.8498,
|
| 210 |
+
"step": 11500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.4683475138552806,
|
| 214 |
+
"grad_norm": 57106.34375,
|
| 215 |
+
"learning_rate": 2.1266099445788778e-05,
|
| 216 |
+
"loss": 0.8723,
|
| 217 |
+
"step": 12000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.4683475138552806,
|
| 221 |
+
"eval_loss": 0.7961086630821228,
|
| 222 |
+
"eval_runtime": 246.9977,
|
| 223 |
+
"eval_samples_per_second": 87.357,
|
| 224 |
+
"eval_steps_per_second": 5.462,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.48786199359925064,
|
| 229 |
+
"grad_norm": 42744.36328125,
|
| 230 |
+
"learning_rate": 2.0485520256029976e-05,
|
| 231 |
+
"loss": 0.8664,
|
| 232 |
+
"step": 12500
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.5073764733432207,
|
| 236 |
+
"grad_norm": 59340.5859375,
|
| 237 |
+
"learning_rate": 1.9704941066271174e-05,
|
| 238 |
+
"loss": 0.8719,
|
| 239 |
+
"step": 13000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.5268909530871907,
|
| 243 |
+
"grad_norm": 76933.4453125,
|
| 244 |
+
"learning_rate": 1.8924361876512375e-05,
|
| 245 |
+
"loss": 0.8896,
|
| 246 |
+
"step": 13500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.5464054328311607,
|
| 250 |
+
"grad_norm": 38514.16015625,
|
| 251 |
+
"learning_rate": 1.8143782686753573e-05,
|
| 252 |
+
"loss": 0.848,
|
| 253 |
+
"step": 14000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.5464054328311607,
|
| 257 |
+
"eval_loss": 0.7900422811508179,
|
| 258 |
+
"eval_runtime": 247.446,
|
| 259 |
+
"eval_samples_per_second": 87.199,
|
| 260 |
+
"eval_steps_per_second": 5.452,
|
| 261 |
+
"step": 14000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5659199125751307,
|
| 265 |
+
"grad_norm": 37615.3515625,
|
| 266 |
+
"learning_rate": 1.736320349699477e-05,
|
| 267 |
+
"loss": 0.8632,
|
| 268 |
+
"step": 14500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5854343923191008,
|
| 272 |
+
"grad_norm": 81223.0625,
|
| 273 |
+
"learning_rate": 1.6582624307235972e-05,
|
| 274 |
+
"loss": 0.8622,
|
| 275 |
+
"step": 15000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6049488720630708,
|
| 279 |
+
"grad_norm": 54736.93359375,
|
| 280 |
+
"learning_rate": 1.580204511747717e-05,
|
| 281 |
+
"loss": 0.8655,
|
| 282 |
+
"step": 15500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6244633518070408,
|
| 286 |
+
"grad_norm": 45588.96484375,
|
| 287 |
+
"learning_rate": 1.5021465927718368e-05,
|
| 288 |
+
"loss": 0.877,
|
| 289 |
+
"step": 16000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6244633518070408,
|
| 293 |
+
"eval_loss": 0.7854538559913635,
|
| 294 |
+
"eval_runtime": 247.3837,
|
| 295 |
+
"eval_samples_per_second": 87.221,
|
| 296 |
+
"eval_steps_per_second": 5.453,
|
| 297 |
+
"step": 16000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6439778315510108,
|
| 301 |
+
"grad_norm": 43015.6015625,
|
| 302 |
+
"learning_rate": 1.4240886737959567e-05,
|
| 303 |
+
"loss": 0.8687,
|
| 304 |
+
"step": 16500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.6634923112949809,
|
| 308 |
+
"grad_norm": 35532.26171875,
|
| 309 |
+
"learning_rate": 1.3460307548200767e-05,
|
| 310 |
+
"loss": 0.8749,
|
| 311 |
+
"step": 17000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.6830067910389509,
|
| 315 |
+
"grad_norm": 32677.763671875,
|
| 316 |
+
"learning_rate": 1.2679728358441965e-05,
|
| 317 |
+
"loss": 0.8727,
|
| 318 |
+
"step": 17500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7025212707829209,
|
| 322 |
+
"grad_norm": 42200.640625,
|
| 323 |
+
"learning_rate": 1.1899149168683164e-05,
|
| 324 |
+
"loss": 0.862,
|
| 325 |
+
"step": 18000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7025212707829209,
|
| 329 |
+
"eval_loss": 0.7817208170890808,
|
| 330 |
+
"eval_runtime": 247.398,
|
| 331 |
+
"eval_samples_per_second": 87.216,
|
| 332 |
+
"eval_steps_per_second": 5.453,
|
| 333 |
+
"step": 18000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.722035750526891,
|
| 337 |
+
"grad_norm": 30234.58203125,
|
| 338 |
+
"learning_rate": 1.1118569978924364e-05,
|
| 339 |
+
"loss": 0.8432,
|
| 340 |
+
"step": 18500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.741550230270861,
|
| 344 |
+
"grad_norm": 43296.27734375,
|
| 345 |
+
"learning_rate": 1.0337990789165561e-05,
|
| 346 |
+
"loss": 0.8711,
|
| 347 |
+
"step": 19000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.761064710014831,
|
| 351 |
+
"grad_norm": 20832.39453125,
|
| 352 |
+
"learning_rate": 9.557411599406761e-06,
|
| 353 |
+
"loss": 0.8716,
|
| 354 |
+
"step": 19500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.780579189758801,
|
| 358 |
+
"grad_norm": 33938.4140625,
|
| 359 |
+
"learning_rate": 8.77683240964796e-06,
|
| 360 |
+
"loss": 0.8584,
|
| 361 |
+
"step": 20000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.780579189758801,
|
| 365 |
+
"eval_loss": 0.7791029214859009,
|
| 366 |
+
"eval_runtime": 247.0845,
|
| 367 |
+
"eval_samples_per_second": 87.326,
|
| 368 |
+
"eval_steps_per_second": 5.46,
|
| 369 |
+
"step": 20000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.800093669502771,
|
| 373 |
+
"grad_norm": 56116.62109375,
|
| 374 |
+
"learning_rate": 7.996253219889158e-06,
|
| 375 |
+
"loss": 0.8776,
|
| 376 |
+
"step": 20500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.8196081492467411,
|
| 380 |
+
"grad_norm": 33855.76953125,
|
| 381 |
+
"learning_rate": 7.215674030130358e-06,
|
| 382 |
+
"loss": 0.8571,
|
| 383 |
+
"step": 21000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.8391226289907111,
|
| 387 |
+
"grad_norm": 83128.3359375,
|
| 388 |
+
"learning_rate": 6.4350948403715564e-06,
|
| 389 |
+
"loss": 0.8606,
|
| 390 |
+
"step": 21500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.8586371087346811,
|
| 394 |
+
"grad_norm": 32873.78515625,
|
| 395 |
+
"learning_rate": 5.654515650612755e-06,
|
| 396 |
+
"loss": 0.8406,
|
| 397 |
+
"step": 22000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.8586371087346811,
|
| 401 |
+
"eval_loss": 0.777363121509552,
|
| 402 |
+
"eval_runtime": 247.4058,
|
| 403 |
+
"eval_samples_per_second": 87.213,
|
| 404 |
+
"eval_steps_per_second": 5.453,
|
| 405 |
+
"step": 22000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.8781515884786512,
|
| 409 |
+
"grad_norm": 31377.396484375,
|
| 410 |
+
"learning_rate": 4.873936460853954e-06,
|
| 411 |
+
"loss": 0.8368,
|
| 412 |
+
"step": 22500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.8976660682226212,
|
| 416 |
+
"grad_norm": 22825.560546875,
|
| 417 |
+
"learning_rate": 4.093357271095153e-06,
|
| 418 |
+
"loss": 0.8419,
|
| 419 |
+
"step": 23000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.9171805479665912,
|
| 423 |
+
"grad_norm": 39448.79296875,
|
| 424 |
+
"learning_rate": 3.312778081336352e-06,
|
| 425 |
+
"loss": 0.8731,
|
| 426 |
+
"step": 23500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.9366950277105612,
|
| 430 |
+
"grad_norm": 67876.9296875,
|
| 431 |
+
"learning_rate": 2.5321988915775507e-06,
|
| 432 |
+
"loss": 0.8458,
|
| 433 |
+
"step": 24000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.9366950277105612,
|
| 437 |
+
"eval_loss": 0.7763074636459351,
|
| 438 |
+
"eval_runtime": 247.0633,
|
| 439 |
+
"eval_samples_per_second": 87.334,
|
| 440 |
+
"eval_steps_per_second": 5.46,
|
| 441 |
+
"step": 24000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.9562095074545313,
|
| 445 |
+
"grad_norm": 32097.791015625,
|
| 446 |
+
"learning_rate": 1.7516197018187498e-06,
|
| 447 |
+
"loss": 0.8461,
|
| 448 |
+
"step": 24500
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.9757239871985013,
|
| 452 |
+
"grad_norm": 34695.05859375,
|
| 453 |
+
"learning_rate": 9.710405120599484e-07,
|
| 454 |
+
"loss": 0.8384,
|
| 455 |
+
"step": 25000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.9952384669424713,
|
| 459 |
+
"grad_norm": 41189.7265625,
|
| 460 |
+
"learning_rate": 1.9046132230114745e-07,
|
| 461 |
+
"loss": 0.8632,
|
| 462 |
+
"step": 25500
|
| 463 |
+
}
|
| 464 |
+
],
|
| 465 |
+
"logging_steps": 500,
|
| 466 |
+
"max_steps": 25622,
|
| 467 |
+
"num_input_tokens_seen": 0,
|
| 468 |
+
"num_train_epochs": 1,
|
| 469 |
+
"save_steps": 2000,
|
| 470 |
+
"stateful_callbacks": {
|
| 471 |
+
"TrainerControl": {
|
| 472 |
+
"args": {
|
| 473 |
+
"should_epoch_stop": false,
|
| 474 |
+
"should_evaluate": false,
|
| 475 |
+
"should_log": false,
|
| 476 |
+
"should_save": true,
|
| 477 |
+
"should_training_stop": true
|
| 478 |
+
},
|
| 479 |
+
"attributes": {}
|
| 480 |
+
}
|
| 481 |
+
},
|
| 482 |
+
"total_flos": 5.548269480443904e+16,
|
| 483 |
+
"train_batch_size": 16,
|
| 484 |
+
"trial_name": null,
|
| 485 |
+
"trial_params": null
|
| 486 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:becadaf22ea19df84f2c88957e975a2593d93d1dcd81142c7c618ec7ae42d153
|
| 3 |
+
size 5432
|