upload flan dialogue summary checkpoint
Browse files- config.json +61 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +468 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.27.2",
|
| 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": "4.27.2"
|
| 7 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edd71738541229c729e50d1bda7c29049a2ca5920f173c34bd2cdc27e9a5fa38
|
| 3 |
+
size 1980790149
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a842404c48dfe3227b10ecaa927d2e9f39b1c598ea7b2b221c35ddbd6c493799
|
| 3 |
+
size 990408885
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f7d8204e7b1526587690f1e38fde9610f66ca0de1767ba6af2331793c0cbf21
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d33c264c21acad66b94bb8201538053bc92b569e972bb89f038ad48526d9f119
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,468 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 31150,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 9.94649545211343e-06,
|
| 13 |
+
"loss": 4.4121,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.32,
|
| 18 |
+
"learning_rate": 9.892990904226861e-06,
|
| 19 |
+
"loss": 0.1731,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.48,
|
| 24 |
+
"learning_rate": 9.83948635634029e-06,
|
| 25 |
+
"loss": 0.1161,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.64,
|
| 30 |
+
"learning_rate": 9.78598180845372e-06,
|
| 31 |
+
"loss": 0.1059,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.8,
|
| 36 |
+
"learning_rate": 9.73247726056715e-06,
|
| 37 |
+
"loss": 0.1011,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.96,
|
| 42 |
+
"learning_rate": 9.67897271268058e-06,
|
| 43 |
+
"loss": 0.1013,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 0.08340005576610565,
|
| 49 |
+
"eval_runtime": 17.1185,
|
| 50 |
+
"eval_samples_per_second": 29.208,
|
| 51 |
+
"eval_steps_per_second": 7.302,
|
| 52 |
+
"step": 3115
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.12,
|
| 56 |
+
"learning_rate": 9.62546816479401e-06,
|
| 57 |
+
"loss": 0.0987,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.28,
|
| 62 |
+
"learning_rate": 9.571963616907438e-06,
|
| 63 |
+
"loss": 0.0946,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.44,
|
| 68 |
+
"learning_rate": 9.518459069020868e-06,
|
| 69 |
+
"loss": 0.0956,
|
| 70 |
+
"step": 4500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.61,
|
| 74 |
+
"learning_rate": 9.464954521134298e-06,
|
| 75 |
+
"loss": 0.0984,
|
| 76 |
+
"step": 5000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.77,
|
| 80 |
+
"learning_rate": 9.411449973247728e-06,
|
| 81 |
+
"loss": 0.0949,
|
| 82 |
+
"step": 5500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.93,
|
| 86 |
+
"learning_rate": 9.357945425361158e-06,
|
| 87 |
+
"loss": 0.0929,
|
| 88 |
+
"step": 6000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.0,
|
| 92 |
+
"eval_loss": 0.08016223460435867,
|
| 93 |
+
"eval_runtime": 17.1151,
|
| 94 |
+
"eval_samples_per_second": 29.214,
|
| 95 |
+
"eval_steps_per_second": 7.304,
|
| 96 |
+
"step": 6230
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.09,
|
| 100 |
+
"learning_rate": 9.304440877474586e-06,
|
| 101 |
+
"loss": 0.0909,
|
| 102 |
+
"step": 6500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.25,
|
| 106 |
+
"learning_rate": 9.250936329588016e-06,
|
| 107 |
+
"loss": 0.0917,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.41,
|
| 112 |
+
"learning_rate": 9.197431781701446e-06,
|
| 113 |
+
"loss": 0.0913,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.57,
|
| 118 |
+
"learning_rate": 9.143927233814876e-06,
|
| 119 |
+
"loss": 0.0912,
|
| 120 |
+
"step": 8000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.73,
|
| 124 |
+
"learning_rate": 9.090422685928304e-06,
|
| 125 |
+
"loss": 0.0904,
|
| 126 |
+
"step": 8500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.89,
|
| 130 |
+
"learning_rate": 9.036918138041734e-06,
|
| 131 |
+
"loss": 0.0908,
|
| 132 |
+
"step": 9000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.0,
|
| 136 |
+
"eval_loss": 0.0781576856970787,
|
| 137 |
+
"eval_runtime": 17.0736,
|
| 138 |
+
"eval_samples_per_second": 29.285,
|
| 139 |
+
"eval_steps_per_second": 7.321,
|
| 140 |
+
"step": 9345
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.05,
|
| 144 |
+
"learning_rate": 8.983413590155164e-06,
|
| 145 |
+
"loss": 0.089,
|
| 146 |
+
"step": 9500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.21,
|
| 150 |
+
"learning_rate": 8.929909042268593e-06,
|
| 151 |
+
"loss": 0.0874,
|
| 152 |
+
"step": 10000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.37,
|
| 156 |
+
"learning_rate": 8.876404494382023e-06,
|
| 157 |
+
"loss": 0.0868,
|
| 158 |
+
"step": 10500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.53,
|
| 162 |
+
"learning_rate": 8.822899946495453e-06,
|
| 163 |
+
"loss": 0.0868,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.69,
|
| 168 |
+
"learning_rate": 8.769395398608883e-06,
|
| 169 |
+
"loss": 0.0877,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.85,
|
| 174 |
+
"learning_rate": 8.715890850722311e-06,
|
| 175 |
+
"loss": 0.0876,
|
| 176 |
+
"step": 12000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.0,
|
| 180 |
+
"eval_loss": 0.07677410542964935,
|
| 181 |
+
"eval_runtime": 17.0783,
|
| 182 |
+
"eval_samples_per_second": 29.277,
|
| 183 |
+
"eval_steps_per_second": 7.319,
|
| 184 |
+
"step": 12460
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.01,
|
| 188 |
+
"learning_rate": 8.662386302835741e-06,
|
| 189 |
+
"loss": 0.0887,
|
| 190 |
+
"step": 12500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.17,
|
| 194 |
+
"learning_rate": 8.608881754949171e-06,
|
| 195 |
+
"loss": 0.0848,
|
| 196 |
+
"step": 13000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 4.33,
|
| 200 |
+
"learning_rate": 8.555377207062601e-06,
|
| 201 |
+
"loss": 0.0825,
|
| 202 |
+
"step": 13500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.49,
|
| 206 |
+
"learning_rate": 8.501872659176031e-06,
|
| 207 |
+
"loss": 0.085,
|
| 208 |
+
"step": 14000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.65,
|
| 212 |
+
"learning_rate": 8.44836811128946e-06,
|
| 213 |
+
"loss": 0.0858,
|
| 214 |
+
"step": 14500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 4.82,
|
| 218 |
+
"learning_rate": 8.39486356340289e-06,
|
| 219 |
+
"loss": 0.0855,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.98,
|
| 224 |
+
"learning_rate": 8.34135901551632e-06,
|
| 225 |
+
"loss": 0.0857,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.0,
|
| 230 |
+
"eval_loss": 0.07618943601846695,
|
| 231 |
+
"eval_runtime": 17.0787,
|
| 232 |
+
"eval_samples_per_second": 29.276,
|
| 233 |
+
"eval_steps_per_second": 7.319,
|
| 234 |
+
"step": 15575
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.14,
|
| 238 |
+
"learning_rate": 8.28785446762975e-06,
|
| 239 |
+
"loss": 0.0833,
|
| 240 |
+
"step": 16000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.3,
|
| 244 |
+
"learning_rate": 8.234349919743178e-06,
|
| 245 |
+
"loss": 0.0819,
|
| 246 |
+
"step": 16500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.46,
|
| 250 |
+
"learning_rate": 8.180845371856608e-06,
|
| 251 |
+
"loss": 0.0842,
|
| 252 |
+
"step": 17000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.62,
|
| 256 |
+
"learning_rate": 8.127340823970038e-06,
|
| 257 |
+
"loss": 0.0814,
|
| 258 |
+
"step": 17500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.78,
|
| 262 |
+
"learning_rate": 8.073836276083468e-06,
|
| 263 |
+
"loss": 0.0828,
|
| 264 |
+
"step": 18000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.94,
|
| 268 |
+
"learning_rate": 8.020331728196898e-06,
|
| 269 |
+
"loss": 0.0847,
|
| 270 |
+
"step": 18500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 6.0,
|
| 274 |
+
"eval_loss": 0.07566038519144058,
|
| 275 |
+
"eval_runtime": 17.0768,
|
| 276 |
+
"eval_samples_per_second": 29.28,
|
| 277 |
+
"eval_steps_per_second": 7.32,
|
| 278 |
+
"step": 18690
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.1,
|
| 282 |
+
"learning_rate": 7.966827180310326e-06,
|
| 283 |
+
"loss": 0.0826,
|
| 284 |
+
"step": 19000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.26,
|
| 288 |
+
"learning_rate": 7.913322632423756e-06,
|
| 289 |
+
"loss": 0.0791,
|
| 290 |
+
"step": 19500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.42,
|
| 294 |
+
"learning_rate": 7.859818084537186e-06,
|
| 295 |
+
"loss": 0.0809,
|
| 296 |
+
"step": 20000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.58,
|
| 300 |
+
"learning_rate": 7.806313536650616e-06,
|
| 301 |
+
"loss": 0.083,
|
| 302 |
+
"step": 20500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.74,
|
| 306 |
+
"learning_rate": 7.752808988764046e-06,
|
| 307 |
+
"loss": 0.0817,
|
| 308 |
+
"step": 21000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.9,
|
| 312 |
+
"learning_rate": 7.699304440877475e-06,
|
| 313 |
+
"loss": 0.0815,
|
| 314 |
+
"step": 21500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.0,
|
| 318 |
+
"eval_loss": 0.07512963563203812,
|
| 319 |
+
"eval_runtime": 17.0959,
|
| 320 |
+
"eval_samples_per_second": 29.247,
|
| 321 |
+
"eval_steps_per_second": 7.312,
|
| 322 |
+
"step": 21805
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 7.06,
|
| 326 |
+
"learning_rate": 7.645799892990905e-06,
|
| 327 |
+
"loss": 0.0812,
|
| 328 |
+
"step": 22000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 7.22,
|
| 332 |
+
"learning_rate": 7.592295345104335e-06,
|
| 333 |
+
"loss": 0.0805,
|
| 334 |
+
"step": 22500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 7.38,
|
| 338 |
+
"learning_rate": 7.538790797217765e-06,
|
| 339 |
+
"loss": 0.0808,
|
| 340 |
+
"step": 23000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 7.54,
|
| 344 |
+
"learning_rate": 7.485286249331194e-06,
|
| 345 |
+
"loss": 0.0792,
|
| 346 |
+
"step": 23500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 7.7,
|
| 350 |
+
"learning_rate": 7.431781701444624e-06,
|
| 351 |
+
"loss": 0.0792,
|
| 352 |
+
"step": 24000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.87,
|
| 356 |
+
"learning_rate": 7.378277153558053e-06,
|
| 357 |
+
"loss": 0.0807,
|
| 358 |
+
"step": 24500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 8.0,
|
| 362 |
+
"eval_loss": 0.07496295124292374,
|
| 363 |
+
"eval_runtime": 17.08,
|
| 364 |
+
"eval_samples_per_second": 29.274,
|
| 365 |
+
"eval_steps_per_second": 7.319,
|
| 366 |
+
"step": 24920
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.03,
|
| 370 |
+
"learning_rate": 7.324772605671483e-06,
|
| 371 |
+
"loss": 0.0784,
|
| 372 |
+
"step": 25000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 8.19,
|
| 376 |
+
"learning_rate": 7.271268057784913e-06,
|
| 377 |
+
"loss": 0.0776,
|
| 378 |
+
"step": 25500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 8.35,
|
| 382 |
+
"learning_rate": 7.217763509898342e-06,
|
| 383 |
+
"loss": 0.0764,
|
| 384 |
+
"step": 26000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.51,
|
| 388 |
+
"learning_rate": 7.164258962011772e-06,
|
| 389 |
+
"loss": 0.0792,
|
| 390 |
+
"step": 26500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 8.67,
|
| 394 |
+
"learning_rate": 7.110754414125201e-06,
|
| 395 |
+
"loss": 0.0802,
|
| 396 |
+
"step": 27000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.83,
|
| 400 |
+
"learning_rate": 7.057249866238631e-06,
|
| 401 |
+
"loss": 0.0803,
|
| 402 |
+
"step": 27500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.99,
|
| 406 |
+
"learning_rate": 7.003745318352061e-06,
|
| 407 |
+
"loss": 0.0779,
|
| 408 |
+
"step": 28000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 9.0,
|
| 412 |
+
"eval_loss": 0.0747738629579544,
|
| 413 |
+
"eval_runtime": 17.0877,
|
| 414 |
+
"eval_samples_per_second": 29.261,
|
| 415 |
+
"eval_steps_per_second": 7.315,
|
| 416 |
+
"step": 28035
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.15,
|
| 420 |
+
"learning_rate": 6.950240770465491e-06,
|
| 421 |
+
"loss": 0.0765,
|
| 422 |
+
"step": 28500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.31,
|
| 426 |
+
"learning_rate": 6.896736222578921e-06,
|
| 427 |
+
"loss": 0.0762,
|
| 428 |
+
"step": 29000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 9.47,
|
| 432 |
+
"learning_rate": 6.84323167469235e-06,
|
| 433 |
+
"loss": 0.0777,
|
| 434 |
+
"step": 29500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 9.63,
|
| 438 |
+
"learning_rate": 6.789727126805778e-06,
|
| 439 |
+
"loss": 0.078,
|
| 440 |
+
"step": 30000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.79,
|
| 444 |
+
"learning_rate": 6.736222578919208e-06,
|
| 445 |
+
"loss": 0.0782,
|
| 446 |
+
"step": 30500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 9.95,
|
| 450 |
+
"learning_rate": 6.682718031032638e-06,
|
| 451 |
+
"loss": 0.0757,
|
| 452 |
+
"step": 31000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.0,
|
| 456 |
+
"eval_loss": 0.07480964064598083,
|
| 457 |
+
"eval_runtime": 17.0749,
|
| 458 |
+
"eval_samples_per_second": 29.283,
|
| 459 |
+
"eval_steps_per_second": 7.321,
|
| 460 |
+
"step": 31150
|
| 461 |
+
}
|
| 462 |
+
],
|
| 463 |
+
"max_steps": 93450,
|
| 464 |
+
"num_train_epochs": 30,
|
| 465 |
+
"total_flos": 8.53207661150208e+16,
|
| 466 |
+
"trial_name": null,
|
| 467 |
+
"trial_params": null
|
| 468 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0fa116c5e3ab65f9b0008617c5a811cff17751cf47eec575f94d2784b55ef9d
|
| 3 |
+
size 3643
|