Initial commit from mrm8488
Browse files- config.json +29 -0
- events.out.tfevents.1629629250.7d47c339fd70.113.1 +3 -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
- trainer_state.json +816 -0
- training_args.bin +3 -0
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": "4.10.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250112
|
| 29 |
+
}
|
events.out.tfevents.1629629250.7d47c339fd70.113.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68c7525ab85e80a90cb14b3f1cfee246e9e6d0136c964775d296981a3b24cfb4
|
| 3 |
+
size 4367
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e1bab0dea6e5c38b76a545e78e3b2abaf649bd9bc3f0daf960c1f7941344a2
|
| 3 |
+
size 2329700301
|
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"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,816 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.414368184733804,
|
| 5 |
+
"global_step": 40000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.959910198845414e-05,
|
| 13 |
+
"loss": 13.3635,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 4.919820397690827e-05,
|
| 19 |
+
"loss": 3.169,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"eval_loss": 0.662490725517273,
|
| 25 |
+
"eval_runtime": 80.6872,
|
| 26 |
+
"eval_samples_per_second": 62.922,
|
| 27 |
+
"eval_steps_per_second": 31.467,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.24,
|
| 32 |
+
"learning_rate": 4.8797305965362415e-05,
|
| 33 |
+
"loss": 0.578,
|
| 34 |
+
"step": 1500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.32,
|
| 38 |
+
"learning_rate": 4.839640795381655e-05,
|
| 39 |
+
"loss": 0.2929,
|
| 40 |
+
"step": 2000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.32,
|
| 44 |
+
"eval_loss": 0.18057043850421906,
|
| 45 |
+
"eval_runtime": 80.3642,
|
| 46 |
+
"eval_samples_per_second": 63.175,
|
| 47 |
+
"eval_steps_per_second": 31.594,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.4,
|
| 52 |
+
"learning_rate": 4.799550994227069e-05,
|
| 53 |
+
"loss": 0.2481,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.48,
|
| 58 |
+
"learning_rate": 4.759461193072483e-05,
|
| 59 |
+
"loss": 0.2159,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.48,
|
| 64 |
+
"eval_loss": 0.1447182148694992,
|
| 65 |
+
"eval_runtime": 80.0634,
|
| 66 |
+
"eval_samples_per_second": 63.412,
|
| 67 |
+
"eval_steps_per_second": 31.712,
|
| 68 |
+
"step": 3000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.56,
|
| 72 |
+
"learning_rate": 4.719371391917896e-05,
|
| 73 |
+
"loss": 0.2131,
|
| 74 |
+
"step": 3500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.64,
|
| 78 |
+
"learning_rate": 4.6792815907633104e-05,
|
| 79 |
+
"loss": 0.1955,
|
| 80 |
+
"step": 4000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.64,
|
| 84 |
+
"eval_loss": 0.13617677986621857,
|
| 85 |
+
"eval_runtime": 80.8812,
|
| 86 |
+
"eval_samples_per_second": 62.771,
|
| 87 |
+
"eval_steps_per_second": 31.392,
|
| 88 |
+
"step": 4000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.72,
|
| 92 |
+
"learning_rate": 4.639191789608724e-05,
|
| 93 |
+
"loss": 0.1799,
|
| 94 |
+
"step": 4500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8,
|
| 98 |
+
"learning_rate": 4.5991019884541375e-05,
|
| 99 |
+
"loss": 0.1785,
|
| 100 |
+
"step": 5000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8,
|
| 104 |
+
"eval_loss": 0.12113407254219055,
|
| 105 |
+
"eval_runtime": 81.0258,
|
| 106 |
+
"eval_samples_per_second": 62.659,
|
| 107 |
+
"eval_steps_per_second": 31.336,
|
| 108 |
+
"step": 5000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.88,
|
| 112 |
+
"learning_rate": 4.559012187299551e-05,
|
| 113 |
+
"loss": 0.1664,
|
| 114 |
+
"step": 5500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.96,
|
| 118 |
+
"learning_rate": 4.5189223861449645e-05,
|
| 119 |
+
"loss": 0.1661,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.96,
|
| 124 |
+
"eval_loss": 0.1217775046825409,
|
| 125 |
+
"eval_runtime": 80.4348,
|
| 126 |
+
"eval_samples_per_second": 63.119,
|
| 127 |
+
"eval_steps_per_second": 31.566,
|
| 128 |
+
"step": 6000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.04,
|
| 132 |
+
"learning_rate": 4.478832584990379e-05,
|
| 133 |
+
"loss": 0.152,
|
| 134 |
+
"step": 6500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.12,
|
| 138 |
+
"learning_rate": 4.438742783835793e-05,
|
| 139 |
+
"loss": 0.1429,
|
| 140 |
+
"step": 7000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.12,
|
| 144 |
+
"eval_loss": 0.11830633133649826,
|
| 145 |
+
"eval_runtime": 80.5584,
|
| 146 |
+
"eval_samples_per_second": 63.023,
|
| 147 |
+
"eval_steps_per_second": 31.518,
|
| 148 |
+
"step": 7000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.2,
|
| 152 |
+
"learning_rate": 4.3986529826812064e-05,
|
| 153 |
+
"loss": 0.1436,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.28,
|
| 158 |
+
"learning_rate": 4.35856318152662e-05,
|
| 159 |
+
"loss": 0.138,
|
| 160 |
+
"step": 8000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.28,
|
| 164 |
+
"eval_loss": 0.11041316390037537,
|
| 165 |
+
"eval_runtime": 80.3972,
|
| 166 |
+
"eval_samples_per_second": 63.149,
|
| 167 |
+
"eval_steps_per_second": 31.581,
|
| 168 |
+
"step": 8000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.36,
|
| 172 |
+
"learning_rate": 4.3184733803720335e-05,
|
| 173 |
+
"loss": 0.139,
|
| 174 |
+
"step": 8500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.44,
|
| 178 |
+
"learning_rate": 4.278383579217447e-05,
|
| 179 |
+
"loss": 0.1328,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.44,
|
| 184 |
+
"eval_loss": 0.11453410983085632,
|
| 185 |
+
"eval_runtime": 80.9914,
|
| 186 |
+
"eval_samples_per_second": 62.686,
|
| 187 |
+
"eval_steps_per_second": 31.349,
|
| 188 |
+
"step": 9000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.52,
|
| 192 |
+
"learning_rate": 4.238293778062861e-05,
|
| 193 |
+
"loss": 0.1336,
|
| 194 |
+
"step": 9500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.6,
|
| 198 |
+
"learning_rate": 4.198203976908275e-05,
|
| 199 |
+
"loss": 0.1257,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.6,
|
| 204 |
+
"eval_loss": 0.11141891777515411,
|
| 205 |
+
"eval_runtime": 80.764,
|
| 206 |
+
"eval_samples_per_second": 62.862,
|
| 207 |
+
"eval_steps_per_second": 31.437,
|
| 208 |
+
"step": 10000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.68,
|
| 212 |
+
"learning_rate": 4.158114175753688e-05,
|
| 213 |
+
"loss": 0.129,
|
| 214 |
+
"step": 10500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.76,
|
| 218 |
+
"learning_rate": 4.118024374599102e-05,
|
| 219 |
+
"loss": 0.1283,
|
| 220 |
+
"step": 11000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.76,
|
| 224 |
+
"eval_loss": 0.10540181398391724,
|
| 225 |
+
"eval_runtime": 80.8099,
|
| 226 |
+
"eval_samples_per_second": 62.826,
|
| 227 |
+
"eval_steps_per_second": 31.419,
|
| 228 |
+
"step": 11000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.84,
|
| 232 |
+
"learning_rate": 4.077934573444516e-05,
|
| 233 |
+
"loss": 0.1329,
|
| 234 |
+
"step": 11500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.92,
|
| 238 |
+
"learning_rate": 4.03784477228993e-05,
|
| 239 |
+
"loss": 0.1233,
|
| 240 |
+
"step": 12000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.92,
|
| 244 |
+
"eval_loss": 0.10773167759180069,
|
| 245 |
+
"eval_runtime": 80.5271,
|
| 246 |
+
"eval_samples_per_second": 63.047,
|
| 247 |
+
"eval_steps_per_second": 31.53,
|
| 248 |
+
"step": 12000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.0,
|
| 252 |
+
"learning_rate": 3.9977549711353436e-05,
|
| 253 |
+
"loss": 0.121,
|
| 254 |
+
"step": 12500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.08,
|
| 258 |
+
"learning_rate": 3.957665169980757e-05,
|
| 259 |
+
"loss": 0.1022,
|
| 260 |
+
"step": 13000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.08,
|
| 264 |
+
"eval_loss": 0.1054486483335495,
|
| 265 |
+
"eval_runtime": 80.727,
|
| 266 |
+
"eval_samples_per_second": 62.891,
|
| 267 |
+
"eval_steps_per_second": 31.452,
|
| 268 |
+
"step": 13000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.16,
|
| 272 |
+
"learning_rate": 3.917575368826171e-05,
|
| 273 |
+
"loss": 0.113,
|
| 274 |
+
"step": 13500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.25,
|
| 278 |
+
"learning_rate": 3.877485567671584e-05,
|
| 279 |
+
"loss": 0.1015,
|
| 280 |
+
"step": 14000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.25,
|
| 284 |
+
"eval_loss": 0.10687392950057983,
|
| 285 |
+
"eval_runtime": 80.3483,
|
| 286 |
+
"eval_samples_per_second": 63.187,
|
| 287 |
+
"eval_steps_per_second": 31.6,
|
| 288 |
+
"step": 14000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.33,
|
| 292 |
+
"learning_rate": 3.8373957665169984e-05,
|
| 293 |
+
"loss": 0.1052,
|
| 294 |
+
"step": 14500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.41,
|
| 298 |
+
"learning_rate": 3.797305965362412e-05,
|
| 299 |
+
"loss": 0.1013,
|
| 300 |
+
"step": 15000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.41,
|
| 304 |
+
"eval_loss": 0.0990850031375885,
|
| 305 |
+
"eval_runtime": 80.592,
|
| 306 |
+
"eval_samples_per_second": 62.996,
|
| 307 |
+
"eval_steps_per_second": 31.504,
|
| 308 |
+
"step": 15000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.49,
|
| 312 |
+
"learning_rate": 3.7572161642078254e-05,
|
| 313 |
+
"loss": 0.1107,
|
| 314 |
+
"step": 15500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.57,
|
| 318 |
+
"learning_rate": 3.7171263630532396e-05,
|
| 319 |
+
"loss": 0.1024,
|
| 320 |
+
"step": 16000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.57,
|
| 324 |
+
"eval_loss": 0.10092990845441818,
|
| 325 |
+
"eval_runtime": 81.1078,
|
| 326 |
+
"eval_samples_per_second": 62.596,
|
| 327 |
+
"eval_steps_per_second": 31.304,
|
| 328 |
+
"step": 16000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.65,
|
| 332 |
+
"learning_rate": 3.677036561898653e-05,
|
| 333 |
+
"loss": 0.0986,
|
| 334 |
+
"step": 16500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.73,
|
| 338 |
+
"learning_rate": 3.6369467607440674e-05,
|
| 339 |
+
"loss": 0.1011,
|
| 340 |
+
"step": 17000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.73,
|
| 344 |
+
"eval_loss": 0.09937073290348053,
|
| 345 |
+
"eval_runtime": 79.8753,
|
| 346 |
+
"eval_samples_per_second": 63.562,
|
| 347 |
+
"eval_steps_per_second": 31.787,
|
| 348 |
+
"step": 17000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.81,
|
| 352 |
+
"learning_rate": 3.596856959589481e-05,
|
| 353 |
+
"loss": 0.1009,
|
| 354 |
+
"step": 17500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.89,
|
| 358 |
+
"learning_rate": 3.5567671584348944e-05,
|
| 359 |
+
"loss": 0.1011,
|
| 360 |
+
"step": 18000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.89,
|
| 364 |
+
"eval_loss": 0.09842894226312637,
|
| 365 |
+
"eval_runtime": 80.4877,
|
| 366 |
+
"eval_samples_per_second": 63.078,
|
| 367 |
+
"eval_steps_per_second": 31.545,
|
| 368 |
+
"step": 18000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.97,
|
| 372 |
+
"learning_rate": 3.516677357280308e-05,
|
| 373 |
+
"loss": 0.1008,
|
| 374 |
+
"step": 18500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.05,
|
| 378 |
+
"learning_rate": 3.4765875561257214e-05,
|
| 379 |
+
"loss": 0.0935,
|
| 380 |
+
"step": 19000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.05,
|
| 384 |
+
"eval_loss": 0.1000189483165741,
|
| 385 |
+
"eval_runtime": 80.5915,
|
| 386 |
+
"eval_samples_per_second": 62.997,
|
| 387 |
+
"eval_steps_per_second": 31.505,
|
| 388 |
+
"step": 19000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.13,
|
| 392 |
+
"learning_rate": 3.436497754971135e-05,
|
| 393 |
+
"loss": 0.0847,
|
| 394 |
+
"step": 19500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 3.21,
|
| 398 |
+
"learning_rate": 3.396407953816549e-05,
|
| 399 |
+
"loss": 0.086,
|
| 400 |
+
"step": 20000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.21,
|
| 404 |
+
"eval_loss": 0.10353543609380722,
|
| 405 |
+
"eval_runtime": 80.3489,
|
| 406 |
+
"eval_samples_per_second": 63.187,
|
| 407 |
+
"eval_steps_per_second": 31.6,
|
| 408 |
+
"step": 20000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.29,
|
| 412 |
+
"learning_rate": 3.3563181526619633e-05,
|
| 413 |
+
"loss": 0.0858,
|
| 414 |
+
"step": 20500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.37,
|
| 418 |
+
"learning_rate": 3.316228351507377e-05,
|
| 419 |
+
"loss": 0.0868,
|
| 420 |
+
"step": 21000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.37,
|
| 424 |
+
"eval_loss": 0.10058429092168808,
|
| 425 |
+
"eval_runtime": 80.7731,
|
| 426 |
+
"eval_samples_per_second": 62.855,
|
| 427 |
+
"eval_steps_per_second": 31.434,
|
| 428 |
+
"step": 21000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.45,
|
| 432 |
+
"learning_rate": 3.2761385503527904e-05,
|
| 433 |
+
"loss": 0.0822,
|
| 434 |
+
"step": 21500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.53,
|
| 438 |
+
"learning_rate": 3.236048749198204e-05,
|
| 439 |
+
"loss": 0.0854,
|
| 440 |
+
"step": 22000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.53,
|
| 444 |
+
"eval_loss": 0.09908822923898697,
|
| 445 |
+
"eval_runtime": 80.4062,
|
| 446 |
+
"eval_samples_per_second": 63.142,
|
| 447 |
+
"eval_steps_per_second": 31.577,
|
| 448 |
+
"step": 22000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.61,
|
| 452 |
+
"learning_rate": 3.195958948043618e-05,
|
| 453 |
+
"loss": 0.0835,
|
| 454 |
+
"step": 22500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 3.69,
|
| 458 |
+
"learning_rate": 3.1558691468890316e-05,
|
| 459 |
+
"loss": 0.0898,
|
| 460 |
+
"step": 23000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 3.69,
|
| 464 |
+
"eval_loss": 0.09145330637693405,
|
| 465 |
+
"eval_runtime": 81.1442,
|
| 466 |
+
"eval_samples_per_second": 62.568,
|
| 467 |
+
"eval_steps_per_second": 31.29,
|
| 468 |
+
"step": 23000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.77,
|
| 472 |
+
"learning_rate": 3.115779345734445e-05,
|
| 473 |
+
"loss": 0.0876,
|
| 474 |
+
"step": 23500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.85,
|
| 478 |
+
"learning_rate": 3.0756895445798587e-05,
|
| 479 |
+
"loss": 0.08,
|
| 480 |
+
"step": 24000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 3.85,
|
| 484 |
+
"eval_loss": 0.09377244859933853,
|
| 485 |
+
"eval_runtime": 80.6911,
|
| 486 |
+
"eval_samples_per_second": 62.919,
|
| 487 |
+
"eval_steps_per_second": 31.466,
|
| 488 |
+
"step": 24000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.93,
|
| 492 |
+
"learning_rate": 3.0355997434252725e-05,
|
| 493 |
+
"loss": 0.091,
|
| 494 |
+
"step": 24500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.01,
|
| 498 |
+
"learning_rate": 2.9955099422706867e-05,
|
| 499 |
+
"loss": 0.0778,
|
| 500 |
+
"step": 25000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.01,
|
| 504 |
+
"eval_loss": 0.09943201392889023,
|
| 505 |
+
"eval_runtime": 80.4527,
|
| 506 |
+
"eval_samples_per_second": 63.105,
|
| 507 |
+
"eval_steps_per_second": 31.559,
|
| 508 |
+
"step": 25000
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 4.09,
|
| 512 |
+
"learning_rate": 2.9554201411161002e-05,
|
| 513 |
+
"loss": 0.0704,
|
| 514 |
+
"step": 25500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 4.17,
|
| 518 |
+
"learning_rate": 2.915330339961514e-05,
|
| 519 |
+
"loss": 0.0699,
|
| 520 |
+
"step": 26000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 4.17,
|
| 524 |
+
"eval_loss": 0.09294962137937546,
|
| 525 |
+
"eval_runtime": 80.2201,
|
| 526 |
+
"eval_samples_per_second": 63.288,
|
| 527 |
+
"eval_steps_per_second": 31.65,
|
| 528 |
+
"step": 26000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.25,
|
| 532 |
+
"learning_rate": 2.8752405388069276e-05,
|
| 533 |
+
"loss": 0.079,
|
| 534 |
+
"step": 26500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 4.33,
|
| 538 |
+
"learning_rate": 2.835150737652341e-05,
|
| 539 |
+
"loss": 0.0754,
|
| 540 |
+
"step": 27000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 4.33,
|
| 544 |
+
"eval_loss": 0.09366082400083542,
|
| 545 |
+
"eval_runtime": 80.2272,
|
| 546 |
+
"eval_samples_per_second": 63.283,
|
| 547 |
+
"eval_steps_per_second": 31.648,
|
| 548 |
+
"step": 27000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.41,
|
| 552 |
+
"learning_rate": 2.7950609364977553e-05,
|
| 553 |
+
"loss": 0.0707,
|
| 554 |
+
"step": 27500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.49,
|
| 558 |
+
"learning_rate": 2.754971135343169e-05,
|
| 559 |
+
"loss": 0.0727,
|
| 560 |
+
"step": 28000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.49,
|
| 564 |
+
"eval_loss": 0.09205422550439835,
|
| 565 |
+
"eval_runtime": 80.3418,
|
| 566 |
+
"eval_samples_per_second": 63.193,
|
| 567 |
+
"eval_steps_per_second": 31.602,
|
| 568 |
+
"step": 28000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 4.57,
|
| 572 |
+
"learning_rate": 2.7148813341885827e-05,
|
| 573 |
+
"loss": 0.0723,
|
| 574 |
+
"step": 28500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.65,
|
| 578 |
+
"learning_rate": 2.6747915330339962e-05,
|
| 579 |
+
"loss": 0.0718,
|
| 580 |
+
"step": 29000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 4.65,
|
| 584 |
+
"eval_loss": 0.09299702942371368,
|
| 585 |
+
"eval_runtime": 80.7661,
|
| 586 |
+
"eval_samples_per_second": 62.861,
|
| 587 |
+
"eval_steps_per_second": 31.436,
|
| 588 |
+
"step": 29000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.73,
|
| 592 |
+
"learning_rate": 2.6347017318794097e-05,
|
| 593 |
+
"loss": 0.0725,
|
| 594 |
+
"step": 29500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 4.81,
|
| 598 |
+
"learning_rate": 2.594611930724824e-05,
|
| 599 |
+
"loss": 0.0741,
|
| 600 |
+
"step": 30000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.81,
|
| 604 |
+
"eval_loss": 0.09144437313079834,
|
| 605 |
+
"eval_runtime": 80.7469,
|
| 606 |
+
"eval_samples_per_second": 62.875,
|
| 607 |
+
"eval_steps_per_second": 31.444,
|
| 608 |
+
"step": 30000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 4.89,
|
| 612 |
+
"learning_rate": 2.5545221295702375e-05,
|
| 613 |
+
"loss": 0.0708,
|
| 614 |
+
"step": 30500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.97,
|
| 618 |
+
"learning_rate": 2.5144323284156513e-05,
|
| 619 |
+
"loss": 0.0687,
|
| 620 |
+
"step": 31000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 4.97,
|
| 624 |
+
"eval_loss": 0.0920889675617218,
|
| 625 |
+
"eval_runtime": 80.5972,
|
| 626 |
+
"eval_samples_per_second": 62.992,
|
| 627 |
+
"eval_steps_per_second": 31.502,
|
| 628 |
+
"step": 31000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 5.05,
|
| 632 |
+
"learning_rate": 2.474342527261065e-05,
|
| 633 |
+
"loss": 0.0677,
|
| 634 |
+
"step": 31500
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 5.13,
|
| 638 |
+
"learning_rate": 2.4342527261064787e-05,
|
| 639 |
+
"loss": 0.0617,
|
| 640 |
+
"step": 32000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 5.13,
|
| 644 |
+
"eval_loss": 0.09358620643615723,
|
| 645 |
+
"eval_runtime": 80.47,
|
| 646 |
+
"eval_samples_per_second": 63.092,
|
| 647 |
+
"eval_steps_per_second": 31.552,
|
| 648 |
+
"step": 32000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 5.21,
|
| 652 |
+
"learning_rate": 2.3941629249518922e-05,
|
| 653 |
+
"loss": 0.0591,
|
| 654 |
+
"step": 32500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 5.29,
|
| 658 |
+
"learning_rate": 2.354073123797306e-05,
|
| 659 |
+
"loss": 0.0609,
|
| 660 |
+
"step": 33000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.29,
|
| 664 |
+
"eval_loss": 0.09032619744539261,
|
| 665 |
+
"eval_runtime": 80.985,
|
| 666 |
+
"eval_samples_per_second": 62.691,
|
| 667 |
+
"eval_steps_per_second": 31.351,
|
| 668 |
+
"step": 33000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 5.37,
|
| 672 |
+
"learning_rate": 2.31398332264272e-05,
|
| 673 |
+
"loss": 0.0657,
|
| 674 |
+
"step": 33500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.45,
|
| 678 |
+
"learning_rate": 2.2738935214881335e-05,
|
| 679 |
+
"loss": 0.0652,
|
| 680 |
+
"step": 34000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 5.45,
|
| 684 |
+
"eval_loss": 0.0909246951341629,
|
| 685 |
+
"eval_runtime": 81.1024,
|
| 686 |
+
"eval_samples_per_second": 62.6,
|
| 687 |
+
"eval_steps_per_second": 31.306,
|
| 688 |
+
"step": 34000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 5.53,
|
| 692 |
+
"learning_rate": 2.233803720333547e-05,
|
| 693 |
+
"loss": 0.0629,
|
| 694 |
+
"step": 34500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 5.61,
|
| 698 |
+
"learning_rate": 2.1937139191789612e-05,
|
| 699 |
+
"loss": 0.0641,
|
| 700 |
+
"step": 35000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 5.61,
|
| 704 |
+
"eval_loss": 0.09035832434892654,
|
| 705 |
+
"eval_runtime": 80.259,
|
| 706 |
+
"eval_samples_per_second": 63.258,
|
| 707 |
+
"eval_steps_per_second": 31.635,
|
| 708 |
+
"step": 35000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.69,
|
| 712 |
+
"learning_rate": 2.1536241180243747e-05,
|
| 713 |
+
"loss": 0.0642,
|
| 714 |
+
"step": 35500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 5.77,
|
| 718 |
+
"learning_rate": 2.1135343168697885e-05,
|
| 719 |
+
"loss": 0.06,
|
| 720 |
+
"step": 36000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.77,
|
| 724 |
+
"eval_loss": 0.09021405130624771,
|
| 725 |
+
"eval_runtime": 80.1923,
|
| 726 |
+
"eval_samples_per_second": 63.31,
|
| 727 |
+
"eval_steps_per_second": 31.661,
|
| 728 |
+
"step": 36000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 5.85,
|
| 732 |
+
"learning_rate": 2.073444515715202e-05,
|
| 733 |
+
"loss": 0.063,
|
| 734 |
+
"step": 36500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 5.93,
|
| 738 |
+
"learning_rate": 2.033354714560616e-05,
|
| 739 |
+
"loss": 0.0643,
|
| 740 |
+
"step": 37000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 5.93,
|
| 744 |
+
"eval_loss": 0.0934990718960762,
|
| 745 |
+
"eval_runtime": 79.9682,
|
| 746 |
+
"eval_samples_per_second": 63.488,
|
| 747 |
+
"eval_steps_per_second": 31.75,
|
| 748 |
+
"step": 37000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 6.01,
|
| 752 |
+
"learning_rate": 1.9932649134060298e-05,
|
| 753 |
+
"loss": 0.0641,
|
| 754 |
+
"step": 37500
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 6.09,
|
| 758 |
+
"learning_rate": 1.9531751122514433e-05,
|
| 759 |
+
"loss": 0.0552,
|
| 760 |
+
"step": 38000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 6.09,
|
| 764 |
+
"eval_loss": 0.09127607196569443,
|
| 765 |
+
"eval_runtime": 81.2206,
|
| 766 |
+
"eval_samples_per_second": 62.509,
|
| 767 |
+
"eval_steps_per_second": 31.261,
|
| 768 |
+
"step": 38000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 6.17,
|
| 772 |
+
"learning_rate": 1.913085311096857e-05,
|
| 773 |
+
"loss": 0.0586,
|
| 774 |
+
"step": 38500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 6.25,
|
| 778 |
+
"learning_rate": 1.8729955099422707e-05,
|
| 779 |
+
"loss": 0.0517,
|
| 780 |
+
"step": 39000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 6.25,
|
| 784 |
+
"eval_loss": 0.09465406835079193,
|
| 785 |
+
"eval_runtime": 80.2376,
|
| 786 |
+
"eval_samples_per_second": 63.275,
|
| 787 |
+
"eval_steps_per_second": 31.644,
|
| 788 |
+
"step": 39000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 6.33,
|
| 792 |
+
"learning_rate": 1.8329057087876845e-05,
|
| 793 |
+
"loss": 0.055,
|
| 794 |
+
"step": 39500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 6.41,
|
| 798 |
+
"learning_rate": 1.7928159076330984e-05,
|
| 799 |
+
"loss": 0.0592,
|
| 800 |
+
"step": 40000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 6.41,
|
| 804 |
+
"eval_loss": 0.08911187946796417,
|
| 805 |
+
"eval_runtime": 80.0512,
|
| 806 |
+
"eval_samples_per_second": 63.422,
|
| 807 |
+
"eval_steps_per_second": 31.717,
|
| 808 |
+
"step": 40000
|
| 809 |
+
}
|
| 810 |
+
],
|
| 811 |
+
"max_steps": 62360,
|
| 812 |
+
"num_train_epochs": 10,
|
| 813 |
+
"total_flos": 1.9182220110515405e+17,
|
| 814 |
+
"trial_name": null,
|
| 815 |
+
"trial_params": null
|
| 816 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13d13c1d61c80ed74a65e6770374cf22559856745f11fdaf63a2ae53865f0c84
|
| 3 |
+
size 2735
|