Initial commit updates
Browse files- all_results.json +13 -0
- config.json +53 -0
- eval_results.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +7 -0
- trainer_state.json +702 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.8997001051902771,
|
| 4 |
+
"eval_runtime": 330.6456,
|
| 5 |
+
"eval_samples": 2598,
|
| 6 |
+
"eval_samples_per_second": 7.857,
|
| 7 |
+
"eval_steps_per_second": 7.857,
|
| 8 |
+
"perplexity": 2.458865599543415,
|
| 9 |
+
"train_runtime": 14442.4553,
|
| 10 |
+
"train_samples": 11353,
|
| 11 |
+
"train_samples_per_second": 3.93,
|
| 12 |
+
"train_steps_per_second": 3.93
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125M",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local",
|
| 17 |
+
"global",
|
| 18 |
+
"local",
|
| 19 |
+
"global",
|
| 20 |
+
"local"
|
| 21 |
+
],
|
| 22 |
+
"attention_types": [
|
| 23 |
+
[
|
| 24 |
+
[
|
| 25 |
+
"global",
|
| 26 |
+
"local"
|
| 27 |
+
],
|
| 28 |
+
6
|
| 29 |
+
]
|
| 30 |
+
],
|
| 31 |
+
"bos_token_id": 50256,
|
| 32 |
+
"embed_dropout": 0,
|
| 33 |
+
"eos_token_id": 50256,
|
| 34 |
+
"gradient_checkpointing": false,
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": null,
|
| 38 |
+
"layer_norm_epsilon": 1e-05,
|
| 39 |
+
"max_position_embeddings": 2048,
|
| 40 |
+
"model_type": "gpt_neo",
|
| 41 |
+
"num_heads": 12,
|
| 42 |
+
"num_layers": 12,
|
| 43 |
+
"resid_dropout": 0,
|
| 44 |
+
"summary_activation": null,
|
| 45 |
+
"summary_first_dropout": 0.1,
|
| 46 |
+
"summary_proj_to_labels": true,
|
| 47 |
+
"summary_type": "cls_index",
|
| 48 |
+
"summary_use_proj": true,
|
| 49 |
+
"transformers_version": "4.7.0.dev0",
|
| 50 |
+
"use_cache": true,
|
| 51 |
+
"vocab_size": 50257,
|
| 52 |
+
"window_size": 256
|
| 53 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.8997001051902771,
|
| 4 |
+
"eval_runtime": 330.6456,
|
| 5 |
+
"eval_samples": 2598,
|
| 6 |
+
"eval_samples_per_second": 7.857,
|
| 7 |
+
"eval_steps_per_second": 7.857,
|
| 8 |
+
"perplexity": 2.458865599543415
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dc3d9f16ff50a9241afa858998d43979bce542cbb185a9909c7eba9138764d3
|
| 3 |
+
size 526021937
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M"}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_runtime": 14442.4553,
|
| 4 |
+
"train_samples": 11353,
|
| 5 |
+
"train_samples_per_second": 3.93,
|
| 6 |
+
"train_steps_per_second": 3.93
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 56765,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 4.9562230247511674e-05,
|
| 13 |
+
"loss": 2.0275,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.912269884611997e-05,
|
| 19 |
+
"loss": 2.0037,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13,
|
| 24 |
+
"learning_rate": 4.868228662027658e-05,
|
| 25 |
+
"loss": 1.9314,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.18,
|
| 30 |
+
"learning_rate": 4.824187439443319e-05,
|
| 31 |
+
"loss": 1.9222,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.22,
|
| 36 |
+
"learning_rate": 4.78014621685898e-05,
|
| 37 |
+
"loss": 1.9162,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.26,
|
| 42 |
+
"learning_rate": 4.736104994274641e-05,
|
| 43 |
+
"loss": 1.77,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31,
|
| 48 |
+
"learning_rate": 4.692151854135471e-05,
|
| 49 |
+
"loss": 1.7844,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.35,
|
| 54 |
+
"learning_rate": 4.648110631551132e-05,
|
| 55 |
+
"loss": 1.8885,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"learning_rate": 4.604069408966793e-05,
|
| 61 |
+
"loss": 1.7094,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.44,
|
| 66 |
+
"learning_rate": 4.560028186382454e-05,
|
| 67 |
+
"loss": 1.8179,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.48,
|
| 72 |
+
"learning_rate": 4.515986963798115e-05,
|
| 73 |
+
"loss": 1.8352,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.53,
|
| 78 |
+
"learning_rate": 4.471945741213776e-05,
|
| 79 |
+
"loss": 1.7946,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.57,
|
| 84 |
+
"learning_rate": 4.427904518629437e-05,
|
| 85 |
+
"loss": 1.7258,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.62,
|
| 90 |
+
"learning_rate": 4.383863296045098e-05,
|
| 91 |
+
"loss": 1.671,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.66,
|
| 96 |
+
"learning_rate": 4.339910155905928e-05,
|
| 97 |
+
"loss": 1.8649,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.7,
|
| 102 |
+
"learning_rate": 4.295868933321589e-05,
|
| 103 |
+
"loss": 1.9734,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.75,
|
| 108 |
+
"learning_rate": 4.25182771073725e-05,
|
| 109 |
+
"loss": 1.8717,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.79,
|
| 114 |
+
"learning_rate": 4.207786488152911e-05,
|
| 115 |
+
"loss": 1.7005,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.84,
|
| 120 |
+
"learning_rate": 4.163745265568572e-05,
|
| 121 |
+
"loss": 1.6136,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.88,
|
| 126 |
+
"learning_rate": 4.1197040429842334e-05,
|
| 127 |
+
"loss": 1.7965,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.92,
|
| 132 |
+
"learning_rate": 4.075662820399894e-05,
|
| 133 |
+
"loss": 1.6852,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.97,
|
| 138 |
+
"learning_rate": 4.031709680260724e-05,
|
| 139 |
+
"loss": 1.5454,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.01,
|
| 144 |
+
"learning_rate": 3.987668457676385e-05,
|
| 145 |
+
"loss": 1.6019,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.06,
|
| 150 |
+
"learning_rate": 3.943627235092046e-05,
|
| 151 |
+
"loss": 1.7469,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.1,
|
| 156 |
+
"learning_rate": 3.8995860125077074e-05,
|
| 157 |
+
"loss": 1.8031,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.15,
|
| 162 |
+
"learning_rate": 3.855544789923368e-05,
|
| 163 |
+
"loss": 1.6901,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.19,
|
| 168 |
+
"learning_rate": 3.811503567339029e-05,
|
| 169 |
+
"loss": 1.6653,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.23,
|
| 174 |
+
"learning_rate": 3.767462344754691e-05,
|
| 175 |
+
"loss": 1.6627,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.28,
|
| 180 |
+
"learning_rate": 3.723421122170352e-05,
|
| 181 |
+
"loss": 1.6196,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.32,
|
| 186 |
+
"learning_rate": 3.679379899586013e-05,
|
| 187 |
+
"loss": 1.7333,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.37,
|
| 192 |
+
"learning_rate": 3.635426759446842e-05,
|
| 193 |
+
"loss": 1.6364,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.41,
|
| 198 |
+
"learning_rate": 3.591385536862503e-05,
|
| 199 |
+
"loss": 1.6258,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.45,
|
| 204 |
+
"learning_rate": 3.547344314278164e-05,
|
| 205 |
+
"loss": 1.7038,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.5,
|
| 210 |
+
"learning_rate": 3.5033030916938255e-05,
|
| 211 |
+
"loss": 1.6104,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.54,
|
| 216 |
+
"learning_rate": 3.459438033999824e-05,
|
| 217 |
+
"loss": 1.707,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.59,
|
| 222 |
+
"learning_rate": 3.415396811415485e-05,
|
| 223 |
+
"loss": 1.6641,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.63,
|
| 228 |
+
"learning_rate": 3.371355588831146e-05,
|
| 229 |
+
"loss": 1.7144,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.67,
|
| 234 |
+
"learning_rate": 3.327314366246807e-05,
|
| 235 |
+
"loss": 1.7934,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.72,
|
| 240 |
+
"learning_rate": 3.283273143662468e-05,
|
| 241 |
+
"loss": 1.6137,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.76,
|
| 246 |
+
"learning_rate": 3.239231921078129e-05,
|
| 247 |
+
"loss": 1.6195,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.81,
|
| 252 |
+
"learning_rate": 3.1951906984937905e-05,
|
| 253 |
+
"loss": 1.6228,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.85,
|
| 258 |
+
"learning_rate": 3.151149475909451e-05,
|
| 259 |
+
"loss": 1.5511,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.89,
|
| 264 |
+
"learning_rate": 3.107196335770281e-05,
|
| 265 |
+
"loss": 1.5842,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.94,
|
| 270 |
+
"learning_rate": 3.063155113185942e-05,
|
| 271 |
+
"loss": 1.6081,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.98,
|
| 276 |
+
"learning_rate": 3.0191138906016033e-05,
|
| 277 |
+
"loss": 1.6629,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.03,
|
| 282 |
+
"learning_rate": 2.975072668017264e-05,
|
| 283 |
+
"loss": 1.6513,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.07,
|
| 288 |
+
"learning_rate": 2.9310314454329253e-05,
|
| 289 |
+
"loss": 1.5899,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.11,
|
| 294 |
+
"learning_rate": 2.8869902228485862e-05,
|
| 295 |
+
"loss": 1.6249,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.16,
|
| 300 |
+
"learning_rate": 2.8429490002642474e-05,
|
| 301 |
+
"loss": 1.6052,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.2,
|
| 306 |
+
"learning_rate": 2.7989077776799083e-05,
|
| 307 |
+
"loss": 1.5361,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.25,
|
| 312 |
+
"learning_rate": 2.7548665550955695e-05,
|
| 313 |
+
"loss": 1.6174,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.29,
|
| 318 |
+
"learning_rate": 2.7108253325112303e-05,
|
| 319 |
+
"loss": 1.5097,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.33,
|
| 324 |
+
"learning_rate": 2.66687219237206e-05,
|
| 325 |
+
"loss": 1.4344,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.38,
|
| 330 |
+
"learning_rate": 2.6228309697877214e-05,
|
| 331 |
+
"loss": 1.6261,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.42,
|
| 336 |
+
"learning_rate": 2.5787897472033822e-05,
|
| 337 |
+
"loss": 1.5999,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.47,
|
| 342 |
+
"learning_rate": 2.5347485246190434e-05,
|
| 343 |
+
"loss": 1.5727,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.51,
|
| 348 |
+
"learning_rate": 2.4907953844798733e-05,
|
| 349 |
+
"loss": 1.5557,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.55,
|
| 354 |
+
"learning_rate": 2.4467541618955345e-05,
|
| 355 |
+
"loss": 1.7235,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.6,
|
| 360 |
+
"learning_rate": 2.4027129393111957e-05,
|
| 361 |
+
"loss": 1.5407,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.64,
|
| 366 |
+
"learning_rate": 2.3586717167268565e-05,
|
| 367 |
+
"loss": 1.5626,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.69,
|
| 372 |
+
"learning_rate": 2.3146304941425177e-05,
|
| 373 |
+
"loss": 1.6137,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.73,
|
| 378 |
+
"learning_rate": 2.2706773540033472e-05,
|
| 379 |
+
"loss": 1.6471,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.77,
|
| 384 |
+
"learning_rate": 2.226636131419008e-05,
|
| 385 |
+
"loss": 1.685,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.82,
|
| 390 |
+
"learning_rate": 2.1825949088346693e-05,
|
| 391 |
+
"loss": 1.5579,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.86,
|
| 396 |
+
"learning_rate": 2.1385536862503305e-05,
|
| 397 |
+
"loss": 1.5701,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.91,
|
| 402 |
+
"learning_rate": 2.0945124636659917e-05,
|
| 403 |
+
"loss": 1.6108,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.95,
|
| 408 |
+
"learning_rate": 2.0505593235268212e-05,
|
| 409 |
+
"loss": 1.6338,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.99,
|
| 414 |
+
"learning_rate": 2.006518100942482e-05,
|
| 415 |
+
"loss": 1.623,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.04,
|
| 420 |
+
"learning_rate": 1.9624768783581433e-05,
|
| 421 |
+
"loss": 1.5039,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.08,
|
| 426 |
+
"learning_rate": 1.918435655773804e-05,
|
| 427 |
+
"loss": 1.6072,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.13,
|
| 432 |
+
"learning_rate": 1.8743944331894657e-05,
|
| 433 |
+
"loss": 1.5008,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.17,
|
| 438 |
+
"learning_rate": 1.8303532106051265e-05,
|
| 439 |
+
"loss": 1.5741,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.22,
|
| 444 |
+
"learning_rate": 1.7863119880207877e-05,
|
| 445 |
+
"loss": 1.4937,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.26,
|
| 450 |
+
"learning_rate": 1.7423588478816172e-05,
|
| 451 |
+
"loss": 1.5352,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.3,
|
| 456 |
+
"learning_rate": 1.698317625297278e-05,
|
| 457 |
+
"loss": 1.6432,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.35,
|
| 462 |
+
"learning_rate": 1.6542764027129393e-05,
|
| 463 |
+
"loss": 1.5811,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.39,
|
| 468 |
+
"learning_rate": 1.6102351801286005e-05,
|
| 469 |
+
"loss": 1.5633,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.44,
|
| 474 |
+
"learning_rate": 1.5661939575442617e-05,
|
| 475 |
+
"loss": 1.5949,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.48,
|
| 480 |
+
"learning_rate": 1.5222408174050912e-05,
|
| 481 |
+
"loss": 1.5309,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.52,
|
| 486 |
+
"learning_rate": 1.4781995948207522e-05,
|
| 487 |
+
"loss": 1.4779,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.57,
|
| 492 |
+
"learning_rate": 1.4341583722364133e-05,
|
| 493 |
+
"loss": 1.5713,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.61,
|
| 498 |
+
"learning_rate": 1.3901171496520743e-05,
|
| 499 |
+
"loss": 1.521,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.66,
|
| 504 |
+
"learning_rate": 1.3461640095129042e-05,
|
| 505 |
+
"loss": 1.558,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.7,
|
| 510 |
+
"learning_rate": 1.3021227869285652e-05,
|
| 511 |
+
"loss": 1.5095,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.74,
|
| 516 |
+
"learning_rate": 1.2580815643442262e-05,
|
| 517 |
+
"loss": 1.4322,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.79,
|
| 522 |
+
"learning_rate": 1.2140403417598874e-05,
|
| 523 |
+
"loss": 1.558,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.83,
|
| 528 |
+
"learning_rate": 1.1700872016207171e-05,
|
| 529 |
+
"loss": 1.5619,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.88,
|
| 534 |
+
"learning_rate": 1.1260459790363781e-05,
|
| 535 |
+
"loss": 1.4401,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.92,
|
| 540 |
+
"learning_rate": 1.0820047564520392e-05,
|
| 541 |
+
"loss": 1.5182,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.96,
|
| 546 |
+
"learning_rate": 1.0379635338677002e-05,
|
| 547 |
+
"loss": 1.5103,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.01,
|
| 552 |
+
"learning_rate": 9.939223112833612e-06,
|
| 553 |
+
"loss": 1.5342,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.05,
|
| 558 |
+
"learning_rate": 9.498810886990224e-06,
|
| 559 |
+
"loss": 1.4571,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.1,
|
| 564 |
+
"learning_rate": 9.059279485598521e-06,
|
| 565 |
+
"loss": 1.4884,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.14,
|
| 570 |
+
"learning_rate": 8.618867259755131e-06,
|
| 571 |
+
"loss": 1.5288,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.18,
|
| 576 |
+
"learning_rate": 8.178455033911742e-06,
|
| 577 |
+
"loss": 1.6157,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.23,
|
| 582 |
+
"learning_rate": 7.738042808068352e-06,
|
| 583 |
+
"loss": 1.5245,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.27,
|
| 588 |
+
"learning_rate": 7.29851140667665e-06,
|
| 589 |
+
"loss": 1.4058,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.32,
|
| 594 |
+
"learning_rate": 6.858099180833261e-06,
|
| 595 |
+
"loss": 1.617,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.36,
|
| 600 |
+
"learning_rate": 6.417686954989871e-06,
|
| 601 |
+
"loss": 1.4707,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 4.4,
|
| 606 |
+
"learning_rate": 5.977274729146481e-06,
|
| 607 |
+
"loss": 1.4786,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 4.45,
|
| 612 |
+
"learning_rate": 5.536862503303092e-06,
|
| 613 |
+
"loss": 1.4711,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.49,
|
| 618 |
+
"learning_rate": 5.097331101911389e-06,
|
| 619 |
+
"loss": 1.4751,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 4.54,
|
| 624 |
+
"learning_rate": 4.6569188760679995e-06,
|
| 625 |
+
"loss": 1.5495,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.58,
|
| 630 |
+
"learning_rate": 4.21650665022461e-06,
|
| 631 |
+
"loss": 1.4748,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.62,
|
| 636 |
+
"learning_rate": 3.7760944243812214e-06,
|
| 637 |
+
"loss": 1.4816,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.67,
|
| 642 |
+
"learning_rate": 3.3356821985378317e-06,
|
| 643 |
+
"loss": 1.5052,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.71,
|
| 648 |
+
"learning_rate": 2.896150797146129e-06,
|
| 649 |
+
"loss": 1.4555,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 4.76,
|
| 654 |
+
"learning_rate": 2.4557385713027396e-06,
|
| 655 |
+
"loss": 1.4899,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.8,
|
| 660 |
+
"learning_rate": 2.01532634545935e-06,
|
| 661 |
+
"loss": 1.4849,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 4.84,
|
| 666 |
+
"learning_rate": 1.5749141196159605e-06,
|
| 667 |
+
"loss": 1.5955,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.89,
|
| 672 |
+
"learning_rate": 1.1345018937725712e-06,
|
| 673 |
+
"loss": 1.4426,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.93,
|
| 678 |
+
"learning_rate": 6.940896679291817e-07,
|
| 679 |
+
"loss": 1.4316,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.98,
|
| 684 |
+
"learning_rate": 2.5367744208579233e-07,
|
| 685 |
+
"loss": 1.5447,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 5.0,
|
| 690 |
+
"step": 56765,
|
| 691 |
+
"total_flos": 4.366478177206272e+16,
|
| 692 |
+
"train_runtime": 14442.4553,
|
| 693 |
+
"train_samples_per_second": 3.93,
|
| 694 |
+
"train_steps_per_second": 3.93
|
| 695 |
+
}
|
| 696 |
+
],
|
| 697 |
+
"max_steps": 56765,
|
| 698 |
+
"num_train_epochs": 5,
|
| 699 |
+
"total_flos": 4.366478177206272e+16,
|
| 700 |
+
"trial_name": null,
|
| 701 |
+
"trial_params": null
|
| 702 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:736fdd71debdd68b9c0b315aca9aa865f4110ad962fb594104f8a94e9e4f3143
|
| 3 |
+
size 2415
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|