Upload 12 files
Browse files- all_results.json +22 -0
- config.json +29 -0
- eval_results.json +10 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +563 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_bleu": 11.1441,
|
| 4 |
+
"eval_gen_len": 45.821,
|
| 5 |
+
"eval_loss": 0.11526955664157867,
|
| 6 |
+
"eval_runtime": 3580.2173,
|
| 7 |
+
"eval_samples": 5357,
|
| 8 |
+
"eval_samples_per_second": 1.496,
|
| 9 |
+
"eval_steps_per_second": 0.374,
|
| 10 |
+
"predict_bleu": 11.0491,
|
| 11 |
+
"predict_gen_len": 56.1832,
|
| 12 |
+
"predict_loss": 0.18866078555583954,
|
| 13 |
+
"predict_runtime": 672.3422,
|
| 14 |
+
"predict_samples": 1288,
|
| 15 |
+
"predict_samples_per_second": 1.916,
|
| 16 |
+
"predict_steps_per_second": 0.479,
|
| 17 |
+
"train_loss": 0.584253704162415,
|
| 18 |
+
"train_runtime": 11332.4023,
|
| 19 |
+
"train_samples": 5357,
|
| 20 |
+
"train_samples_per_second": 23.636,
|
| 21 |
+
"train_steps_per_second": 0.737
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "gated-gelu",
|
| 13 |
+
"initializer_factor": 1.0,
|
| 14 |
+
"is_encoder_decoder": true,
|
| 15 |
+
"layer_norm_epsilon": 1e-06,
|
| 16 |
+
"model_type": "mt5",
|
| 17 |
+
"num_decoder_layers": 12,
|
| 18 |
+
"num_heads": 12,
|
| 19 |
+
"num_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"relative_attention_num_buckets": 32,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"tokenizer_class": "T5Tokenizer",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.12.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250100
|
| 29 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_bleu": 11.1441,
|
| 4 |
+
"eval_gen_len": 45.821,
|
| 5 |
+
"eval_loss": 0.11526955664157867,
|
| 6 |
+
"eval_runtime": 3580.2173,
|
| 7 |
+
"eval_samples": 5357,
|
| 8 |
+
"eval_samples_per_second": 1.496,
|
| 9 |
+
"eval_steps_per_second": 0.374
|
| 10 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu": 11.0491,
|
| 3 |
+
"predict_gen_len": 56.1832,
|
| 4 |
+
"predict_loss": 0.18866078555583954,
|
| 5 |
+
"predict_runtime": 672.3422,
|
| 6 |
+
"predict_samples": 1288,
|
| 7 |
+
"predict_samples_per_second": 1.916,
|
| 8 |
+
"predict_steps_per_second": 0.479
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e60c89f3f240b6bdbf375446eaeab7d6e619b99a890a94500ddd84c98b33770
|
| 3 |
+
size 2329626573
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.584253704162415,
|
| 4 |
+
"train_runtime": 11332.4023,
|
| 5 |
+
"train_samples": 5357,
|
| 6 |
+
"train_samples_per_second": 23.636,
|
| 7 |
+
"train_steps_per_second": 0.737
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,563 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.997014925373136,
|
| 5 |
+
"global_step": 8350,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.6,
|
| 12 |
+
"learning_rate": 0.0009880239520958084,
|
| 13 |
+
"loss": 5.0465,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.2,
|
| 18 |
+
"learning_rate": 0.0009760479041916168,
|
| 19 |
+
"loss": 3.0126,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.79,
|
| 24 |
+
"learning_rate": 0.0009640718562874252,
|
| 25 |
+
"loss": 2.6782,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.39,
|
| 30 |
+
"learning_rate": 0.0009520958083832335,
|
| 31 |
+
"loss": 2.4056,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.99,
|
| 36 |
+
"learning_rate": 0.0009401197604790419,
|
| 37 |
+
"loss": 2.2999,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.59,
|
| 42 |
+
"learning_rate": 0.0009281437125748503,
|
| 43 |
+
"loss": 1.9862,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.19,
|
| 48 |
+
"learning_rate": 0.0009161676646706587,
|
| 49 |
+
"loss": 1.8922,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.79,
|
| 54 |
+
"learning_rate": 0.0009041916167664672,
|
| 55 |
+
"loss": 1.699,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.39,
|
| 60 |
+
"learning_rate": 0.0008922155688622756,
|
| 61 |
+
"loss": 1.5454,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.99,
|
| 66 |
+
"learning_rate": 0.0008802395209580839,
|
| 67 |
+
"loss": 1.4636,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.59,
|
| 72 |
+
"learning_rate": 0.0008682634730538922,
|
| 73 |
+
"loss": 1.2505,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 7.19,
|
| 78 |
+
"learning_rate": 0.0008562874251497006,
|
| 79 |
+
"loss": 1.1771,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 7.78,
|
| 84 |
+
"learning_rate": 0.000844311377245509,
|
| 85 |
+
"loss": 1.0694,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.38,
|
| 90 |
+
"learning_rate": 0.0008323353293413174,
|
| 91 |
+
"loss": 0.9962,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 8.98,
|
| 96 |
+
"learning_rate": 0.0008203592814371258,
|
| 97 |
+
"loss": 0.9573,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 9.58,
|
| 102 |
+
"learning_rate": 0.0008083832335329342,
|
| 103 |
+
"loss": 0.8383,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 10.18,
|
| 108 |
+
"learning_rate": 0.0007964071856287425,
|
| 109 |
+
"loss": 0.813,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 10.78,
|
| 114 |
+
"learning_rate": 0.0007844311377245509,
|
| 115 |
+
"loss": 0.7532,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 11.38,
|
| 120 |
+
"learning_rate": 0.0007724550898203593,
|
| 121 |
+
"loss": 0.6846,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 11.97,
|
| 126 |
+
"learning_rate": 0.0007604790419161677,
|
| 127 |
+
"loss": 0.6736,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 11.97,
|
| 132 |
+
"eval_bleu": 2.5636,
|
| 133 |
+
"eval_gen_len": 15.2363,
|
| 134 |
+
"eval_loss": 0.29240211844444275,
|
| 135 |
+
"eval_runtime": 438.109,
|
| 136 |
+
"eval_samples_per_second": 12.228,
|
| 137 |
+
"eval_steps_per_second": 3.059,
|
| 138 |
+
"step": 2000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 12.57,
|
| 142 |
+
"learning_rate": 0.0007485029940119761,
|
| 143 |
+
"loss": 0.5751,
|
| 144 |
+
"step": 2100
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 13.17,
|
| 148 |
+
"learning_rate": 0.0007365269461077845,
|
| 149 |
+
"loss": 0.5731,
|
| 150 |
+
"step": 2200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 13.77,
|
| 154 |
+
"learning_rate": 0.0007245508982035929,
|
| 155 |
+
"loss": 0.527,
|
| 156 |
+
"step": 2300
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 14.37,
|
| 160 |
+
"learning_rate": 0.0007125748502994012,
|
| 161 |
+
"loss": 0.5077,
|
| 162 |
+
"step": 2400
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 14.97,
|
| 166 |
+
"learning_rate": 0.0007005988023952096,
|
| 167 |
+
"loss": 0.4783,
|
| 168 |
+
"step": 2500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 15.57,
|
| 172 |
+
"learning_rate": 0.000688622754491018,
|
| 173 |
+
"loss": 0.4261,
|
| 174 |
+
"step": 2600
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 16.17,
|
| 178 |
+
"learning_rate": 0.0006766467065868264,
|
| 179 |
+
"loss": 0.4283,
|
| 180 |
+
"step": 2700
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 16.76,
|
| 184 |
+
"learning_rate": 0.0006646706586826347,
|
| 185 |
+
"loss": 0.3955,
|
| 186 |
+
"step": 2800
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 17.36,
|
| 190 |
+
"learning_rate": 0.0006526946107784431,
|
| 191 |
+
"loss": 0.3785,
|
| 192 |
+
"step": 2900
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 17.96,
|
| 196 |
+
"learning_rate": 0.0006407185628742515,
|
| 197 |
+
"loss": 0.3739,
|
| 198 |
+
"step": 3000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 18.56,
|
| 202 |
+
"learning_rate": 0.0006287425149700598,
|
| 203 |
+
"loss": 0.3335,
|
| 204 |
+
"step": 3100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 19.16,
|
| 208 |
+
"learning_rate": 0.0006167664670658682,
|
| 209 |
+
"loss": 0.3438,
|
| 210 |
+
"step": 3200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 19.76,
|
| 214 |
+
"learning_rate": 0.0006047904191616766,
|
| 215 |
+
"loss": 0.3164,
|
| 216 |
+
"step": 3300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 20.36,
|
| 220 |
+
"learning_rate": 0.000592814371257485,
|
| 221 |
+
"loss": 0.3068,
|
| 222 |
+
"step": 3400
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 20.96,
|
| 226 |
+
"learning_rate": 0.0005808383233532934,
|
| 227 |
+
"loss": 0.3188,
|
| 228 |
+
"step": 3500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 21.56,
|
| 232 |
+
"learning_rate": 0.0005688622754491018,
|
| 233 |
+
"loss": 0.288,
|
| 234 |
+
"step": 3600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 22.16,
|
| 238 |
+
"learning_rate": 0.0005568862275449101,
|
| 239 |
+
"loss": 0.2916,
|
| 240 |
+
"step": 3700
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 22.75,
|
| 244 |
+
"learning_rate": 0.0005449101796407185,
|
| 245 |
+
"loss": 0.2731,
|
| 246 |
+
"step": 3800
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 23.35,
|
| 250 |
+
"learning_rate": 0.000532934131736527,
|
| 251 |
+
"loss": 0.2655,
|
| 252 |
+
"step": 3900
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 23.95,
|
| 256 |
+
"learning_rate": 0.0005209580838323354,
|
| 257 |
+
"loss": 0.2621,
|
| 258 |
+
"step": 4000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 23.95,
|
| 262 |
+
"eval_bleu": 3.3704,
|
| 263 |
+
"eval_gen_len": 16.0834,
|
| 264 |
+
"eval_loss": 0.1354922354221344,
|
| 265 |
+
"eval_runtime": 461.5346,
|
| 266 |
+
"eval_samples_per_second": 11.607,
|
| 267 |
+
"eval_steps_per_second": 2.903,
|
| 268 |
+
"step": 4000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 24.55,
|
| 272 |
+
"learning_rate": 0.0005089820359281438,
|
| 273 |
+
"loss": 0.2493,
|
| 274 |
+
"step": 4100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 25.15,
|
| 278 |
+
"learning_rate": 0.0004970059880239521,
|
| 279 |
+
"loss": 0.2502,
|
| 280 |
+
"step": 4200
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 25.75,
|
| 284 |
+
"learning_rate": 0.00048502994011976046,
|
| 285 |
+
"loss": 0.237,
|
| 286 |
+
"step": 4300
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 26.35,
|
| 290 |
+
"learning_rate": 0.00047305389221556887,
|
| 291 |
+
"loss": 0.2322,
|
| 292 |
+
"step": 4400
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 26.94,
|
| 296 |
+
"learning_rate": 0.00046107784431137727,
|
| 297 |
+
"loss": 0.2356,
|
| 298 |
+
"step": 4500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 27.54,
|
| 302 |
+
"learning_rate": 0.0004491017964071856,
|
| 303 |
+
"loss": 0.2194,
|
| 304 |
+
"step": 4600
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 28.14,
|
| 308 |
+
"learning_rate": 0.00043712574850299403,
|
| 309 |
+
"loss": 0.2181,
|
| 310 |
+
"step": 4700
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 28.74,
|
| 314 |
+
"learning_rate": 0.00042514970059880243,
|
| 315 |
+
"loss": 0.2113,
|
| 316 |
+
"step": 4800
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 29.34,
|
| 320 |
+
"learning_rate": 0.0004131736526946108,
|
| 321 |
+
"loss": 0.2087,
|
| 322 |
+
"step": 4900
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 29.94,
|
| 326 |
+
"learning_rate": 0.0004011976047904192,
|
| 327 |
+
"loss": 0.214,
|
| 328 |
+
"step": 5000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 30.54,
|
| 332 |
+
"learning_rate": 0.0003892215568862276,
|
| 333 |
+
"loss": 0.2028,
|
| 334 |
+
"step": 5100
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 31.14,
|
| 338 |
+
"learning_rate": 0.0003772455089820359,
|
| 339 |
+
"loss": 0.2036,
|
| 340 |
+
"step": 5200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 31.73,
|
| 344 |
+
"learning_rate": 0.0003652694610778443,
|
| 345 |
+
"loss": 0.1953,
|
| 346 |
+
"step": 5300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 32.33,
|
| 350 |
+
"learning_rate": 0.0003532934131736527,
|
| 351 |
+
"loss": 0.1926,
|
| 352 |
+
"step": 5400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 32.93,
|
| 356 |
+
"learning_rate": 0.0003413173652694611,
|
| 357 |
+
"loss": 0.1974,
|
| 358 |
+
"step": 5500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 33.53,
|
| 362 |
+
"learning_rate": 0.00032934131736526946,
|
| 363 |
+
"loss": 0.1866,
|
| 364 |
+
"step": 5600
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 34.13,
|
| 368 |
+
"learning_rate": 0.00031736526946107786,
|
| 369 |
+
"loss": 0.1839,
|
| 370 |
+
"step": 5700
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 34.73,
|
| 374 |
+
"learning_rate": 0.00030538922155688627,
|
| 375 |
+
"loss": 0.1816,
|
| 376 |
+
"step": 5800
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 35.33,
|
| 380 |
+
"learning_rate": 0.0002934131736526946,
|
| 381 |
+
"loss": 0.1837,
|
| 382 |
+
"step": 5900
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 35.93,
|
| 386 |
+
"learning_rate": 0.000281437125748503,
|
| 387 |
+
"loss": 0.1775,
|
| 388 |
+
"step": 6000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 35.93,
|
| 392 |
+
"eval_bleu": 3.6961,
|
| 393 |
+
"eval_gen_len": 16.5854,
|
| 394 |
+
"eval_loss": 0.12107560783624649,
|
| 395 |
+
"eval_runtime": 477.8329,
|
| 396 |
+
"eval_samples_per_second": 11.211,
|
| 397 |
+
"eval_steps_per_second": 2.804,
|
| 398 |
+
"step": 6000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 36.53,
|
| 402 |
+
"learning_rate": 0.0002694610778443114,
|
| 403 |
+
"loss": 0.1742,
|
| 404 |
+
"step": 6100
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 37.13,
|
| 408 |
+
"learning_rate": 0.0002574850299401197,
|
| 409 |
+
"loss": 0.176,
|
| 410 |
+
"step": 6200
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 37.72,
|
| 414 |
+
"learning_rate": 0.00024550898203592813,
|
| 415 |
+
"loss": 0.1704,
|
| 416 |
+
"step": 6300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 38.32,
|
| 420 |
+
"learning_rate": 0.00023353293413173654,
|
| 421 |
+
"loss": 0.1734,
|
| 422 |
+
"step": 6400
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 38.92,
|
| 426 |
+
"learning_rate": 0.0002215568862275449,
|
| 427 |
+
"loss": 0.1662,
|
| 428 |
+
"step": 6500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 39.52,
|
| 432 |
+
"learning_rate": 0.0002095808383233533,
|
| 433 |
+
"loss": 0.1653,
|
| 434 |
+
"step": 6600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 40.12,
|
| 438 |
+
"learning_rate": 0.0001976047904191617,
|
| 439 |
+
"loss": 0.1684,
|
| 440 |
+
"step": 6700
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 40.72,
|
| 444 |
+
"learning_rate": 0.00018562874251497005,
|
| 445 |
+
"loss": 0.1584,
|
| 446 |
+
"step": 6800
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 41.32,
|
| 450 |
+
"learning_rate": 0.00017365269461077845,
|
| 451 |
+
"loss": 0.1622,
|
| 452 |
+
"step": 6900
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 41.91,
|
| 456 |
+
"learning_rate": 0.00016167664670658683,
|
| 457 |
+
"loss": 0.1625,
|
| 458 |
+
"step": 7000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 42.51,
|
| 462 |
+
"learning_rate": 0.0001497005988023952,
|
| 463 |
+
"loss": 0.1558,
|
| 464 |
+
"step": 7100
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 43.11,
|
| 468 |
+
"learning_rate": 0.00013772455089820359,
|
| 469 |
+
"loss": 0.157,
|
| 470 |
+
"step": 7200
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 43.71,
|
| 474 |
+
"learning_rate": 0.00012574850299401196,
|
| 475 |
+
"loss": 0.1568,
|
| 476 |
+
"step": 7300
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 44.31,
|
| 480 |
+
"learning_rate": 0.00011377245508982036,
|
| 481 |
+
"loss": 0.1537,
|
| 482 |
+
"step": 7400
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 44.91,
|
| 486 |
+
"learning_rate": 0.00010179640718562875,
|
| 487 |
+
"loss": 0.1521,
|
| 488 |
+
"step": 7500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 45.51,
|
| 492 |
+
"learning_rate": 8.982035928143712e-05,
|
| 493 |
+
"loss": 0.1508,
|
| 494 |
+
"step": 7600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 46.11,
|
| 498 |
+
"learning_rate": 7.784431137724552e-05,
|
| 499 |
+
"loss": 0.149,
|
| 500 |
+
"step": 7700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 46.7,
|
| 504 |
+
"learning_rate": 6.58682634730539e-05,
|
| 505 |
+
"loss": 0.1462,
|
| 506 |
+
"step": 7800
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 47.3,
|
| 510 |
+
"learning_rate": 5.389221556886228e-05,
|
| 511 |
+
"loss": 0.1484,
|
| 512 |
+
"step": 7900
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 47.9,
|
| 516 |
+
"learning_rate": 4.191616766467066e-05,
|
| 517 |
+
"loss": 0.1478,
|
| 518 |
+
"step": 8000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 47.9,
|
| 522 |
+
"eval_bleu": 3.681,
|
| 523 |
+
"eval_gen_len": 16.4697,
|
| 524 |
+
"eval_loss": 0.11556760966777802,
|
| 525 |
+
"eval_runtime": 415.7833,
|
| 526 |
+
"eval_samples_per_second": 12.884,
|
| 527 |
+
"eval_steps_per_second": 3.223,
|
| 528 |
+
"step": 8000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 48.5,
|
| 532 |
+
"learning_rate": 2.994011976047904e-05,
|
| 533 |
+
"loss": 0.1449,
|
| 534 |
+
"step": 8100
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 49.1,
|
| 538 |
+
"learning_rate": 1.7964071856287426e-05,
|
| 539 |
+
"loss": 0.1448,
|
| 540 |
+
"step": 8200
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 49.7,
|
| 544 |
+
"learning_rate": 5.9880239520958085e-06,
|
| 545 |
+
"loss": 0.1425,
|
| 546 |
+
"step": 8300
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 50.0,
|
| 550 |
+
"step": 8350,
|
| 551 |
+
"total_flos": 6.461676347272704e+16,
|
| 552 |
+
"train_loss": 0.584253704162415,
|
| 553 |
+
"train_runtime": 11332.4023,
|
| 554 |
+
"train_samples_per_second": 23.636,
|
| 555 |
+
"train_steps_per_second": 0.737
|
| 556 |
+
}
|
| 557 |
+
],
|
| 558 |
+
"max_steps": 8350,
|
| 559 |
+
"num_train_epochs": 50,
|
| 560 |
+
"total_flos": 6.461676347272704e+16,
|
| 561 |
+
"trial_name": null,
|
| 562 |
+
"trial_params": null
|
| 563 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be7b42a2a0105b710dd0b059aa308336623237bbb3588d26b8ddaa4770b125de
|
| 3 |
+
size 2927
|