End of training
Browse files- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- trainer_state.json +185 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"name_or_path": "google/flan-t5-base",
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sp_model_kwargs": {},
|
| 110 |
+
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6162260174751282,
|
| 3 |
+
"best_model_checkpoint": "flan_t5_summarization/checkpoint-2720",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 2720,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_gen_len": 19.0,
|
| 13 |
+
"eval_loss": 1.120025634765625,
|
| 14 |
+
"eval_rouge1": 9.2565,
|
| 15 |
+
"eval_rouge2": 1.2805,
|
| 16 |
+
"eval_rougeL": 9.2358,
|
| 17 |
+
"eval_rougeLsum": 9.284,
|
| 18 |
+
"eval_runtime": 4.0606,
|
| 19 |
+
"eval_samples_per_second": 16.5,
|
| 20 |
+
"eval_steps_per_second": 1.478,
|
| 21 |
+
"step": 272
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.84,
|
| 25 |
+
"learning_rate": 4.0808823529411765e-05,
|
| 26 |
+
"loss": 1.5343,
|
| 27 |
+
"step": 500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"eval_gen_len": 19.0,
|
| 32 |
+
"eval_loss": 0.8922988772392273,
|
| 33 |
+
"eval_rouge1": 10.9045,
|
| 34 |
+
"eval_rouge2": 2.9468,
|
| 35 |
+
"eval_rougeL": 10.9112,
|
| 36 |
+
"eval_rougeLsum": 10.8827,
|
| 37 |
+
"eval_runtime": 4.0719,
|
| 38 |
+
"eval_samples_per_second": 16.454,
|
| 39 |
+
"eval_steps_per_second": 1.474,
|
| 40 |
+
"step": 544
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"eval_gen_len": 19.0,
|
| 45 |
+
"eval_loss": 0.7884227633476257,
|
| 46 |
+
"eval_rouge1": 13.637,
|
| 47 |
+
"eval_rouge2": 4.8447,
|
| 48 |
+
"eval_rougeL": 13.3594,
|
| 49 |
+
"eval_rougeLsum": 13.3459,
|
| 50 |
+
"eval_runtime": 4.0204,
|
| 51 |
+
"eval_samples_per_second": 16.665,
|
| 52 |
+
"eval_steps_per_second": 1.492,
|
| 53 |
+
"step": 816
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.68,
|
| 57 |
+
"learning_rate": 3.161764705882353e-05,
|
| 58 |
+
"loss": 0.9949,
|
| 59 |
+
"step": 1000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_gen_len": 18.91044776119403,
|
| 64 |
+
"eval_loss": 0.7256659269332886,
|
| 65 |
+
"eval_rouge1": 15.2005,
|
| 66 |
+
"eval_rouge2": 6.3919,
|
| 67 |
+
"eval_rougeL": 14.781,
|
| 68 |
+
"eval_rougeLsum": 14.7204,
|
| 69 |
+
"eval_runtime": 4.0736,
|
| 70 |
+
"eval_samples_per_second": 16.447,
|
| 71 |
+
"eval_steps_per_second": 1.473,
|
| 72 |
+
"step": 1088
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.0,
|
| 76 |
+
"eval_gen_len": 18.73134328358209,
|
| 77 |
+
"eval_loss": 0.6852018237113953,
|
| 78 |
+
"eval_rouge1": 15.1627,
|
| 79 |
+
"eval_rouge2": 6.3116,
|
| 80 |
+
"eval_rougeL": 14.7187,
|
| 81 |
+
"eval_rougeLsum": 14.6983,
|
| 82 |
+
"eval_runtime": 4.0455,
|
| 83 |
+
"eval_samples_per_second": 16.561,
|
| 84 |
+
"eval_steps_per_second": 1.483,
|
| 85 |
+
"step": 1360
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.51,
|
| 89 |
+
"learning_rate": 2.2426470588235296e-05,
|
| 90 |
+
"loss": 0.8504,
|
| 91 |
+
"step": 1500
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.0,
|
| 95 |
+
"eval_gen_len": 18.73134328358209,
|
| 96 |
+
"eval_loss": 0.6580936312675476,
|
| 97 |
+
"eval_rouge1": 16.0795,
|
| 98 |
+
"eval_rouge2": 6.9284,
|
| 99 |
+
"eval_rougeL": 15.3516,
|
| 100 |
+
"eval_rougeLsum": 15.3571,
|
| 101 |
+
"eval_runtime": 4.0423,
|
| 102 |
+
"eval_samples_per_second": 16.575,
|
| 103 |
+
"eval_steps_per_second": 1.484,
|
| 104 |
+
"step": 1632
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"eval_gen_len": 18.91044776119403,
|
| 109 |
+
"eval_loss": 0.6391794681549072,
|
| 110 |
+
"eval_rouge1": 16.0518,
|
| 111 |
+
"eval_rouge2": 6.9377,
|
| 112 |
+
"eval_rougeL": 15.3914,
|
| 113 |
+
"eval_rougeLsum": 15.3748,
|
| 114 |
+
"eval_runtime": 4.0453,
|
| 115 |
+
"eval_samples_per_second": 16.562,
|
| 116 |
+
"eval_steps_per_second": 1.483,
|
| 117 |
+
"step": 1904
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 7.35,
|
| 121 |
+
"learning_rate": 1.323529411764706e-05,
|
| 122 |
+
"loss": 0.7841,
|
| 123 |
+
"step": 2000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.0,
|
| 127 |
+
"eval_gen_len": 18.82089552238806,
|
| 128 |
+
"eval_loss": 0.6258341073989868,
|
| 129 |
+
"eval_rouge1": 16.1307,
|
| 130 |
+
"eval_rouge2": 7.6286,
|
| 131 |
+
"eval_rougeL": 15.7398,
|
| 132 |
+
"eval_rougeLsum": 15.7627,
|
| 133 |
+
"eval_runtime": 4.0536,
|
| 134 |
+
"eval_samples_per_second": 16.529,
|
| 135 |
+
"eval_steps_per_second": 1.48,
|
| 136 |
+
"step": 2176
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"eval_gen_len": 18.73134328358209,
|
| 141 |
+
"eval_loss": 0.6200478672981262,
|
| 142 |
+
"eval_rouge1": 15.9488,
|
| 143 |
+
"eval_rouge2": 7.4447,
|
| 144 |
+
"eval_rougeL": 15.5654,
|
| 145 |
+
"eval_rougeLsum": 15.583,
|
| 146 |
+
"eval_runtime": 4.042,
|
| 147 |
+
"eval_samples_per_second": 16.576,
|
| 148 |
+
"eval_steps_per_second": 1.484,
|
| 149 |
+
"step": 2448
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 9.19,
|
| 153 |
+
"learning_rate": 4.044117647058824e-06,
|
| 154 |
+
"loss": 0.7599,
|
| 155 |
+
"step": 2500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.0,
|
| 159 |
+
"eval_gen_len": 18.73134328358209,
|
| 160 |
+
"eval_loss": 0.6162260174751282,
|
| 161 |
+
"eval_rouge1": 15.9418,
|
| 162 |
+
"eval_rouge2": 7.4447,
|
| 163 |
+
"eval_rougeL": 15.5655,
|
| 164 |
+
"eval_rougeLsum": 15.5835,
|
| 165 |
+
"eval_runtime": 4.0403,
|
| 166 |
+
"eval_samples_per_second": 16.583,
|
| 167 |
+
"eval_steps_per_second": 1.485,
|
| 168 |
+
"step": 2720
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 10.0,
|
| 172 |
+
"step": 2720,
|
| 173 |
+
"total_flos": 1177555285370880.0,
|
| 174 |
+
"train_loss": 0.9648406533633962,
|
| 175 |
+
"train_runtime": 1843.1414,
|
| 176 |
+
"train_samples_per_second": 17.693,
|
| 177 |
+
"train_steps_per_second": 1.476
|
| 178 |
+
}
|
| 179 |
+
],
|
| 180 |
+
"max_steps": 2720,
|
| 181 |
+
"num_train_epochs": 10,
|
| 182 |
+
"total_flos": 1177555285370880.0,
|
| 183 |
+
"trial_name": null,
|
| 184 |
+
"trial_params": null
|
| 185 |
+
}
|