Upload folder using huggingface_hub
Browse files- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- trainer_state.json +738 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.30.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.30.2"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:127517aa9d5de99ff794b531bb818ffef4ff05da70d15d82875b8e8bee581bc3
|
| 3 |
+
size 1384581
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd821ec60a8052407b277dd1e4bffca920af49a7334a5ca085587287cf85b257
|
| 3 |
+
size 497807197
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d54e3e2cd8494b8cebe1935c61d043471811f9bffc55b5d1606db043fa565a1
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b83bcdcc320b36fc38b057643cb82268f99a7e7642d20842ef096227afd40f5e
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1024,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,738 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.944110060189166,
|
| 5 |
+
"global_step": 11500,
|
| 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": 9.920034393809114e-05,
|
| 13 |
+
"loss": 1.8949,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 9.834049871023217e-05,
|
| 19 |
+
"loss": 1.0475,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13,
|
| 24 |
+
"learning_rate": 9.748065348237318e-05,
|
| 25 |
+
"loss": 1.0269,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.17,
|
| 30 |
+
"learning_rate": 9.66208082545142e-05,
|
| 31 |
+
"loss": 1.0098,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.21,
|
| 36 |
+
"learning_rate": 9.57609630266552e-05,
|
| 37 |
+
"loss": 0.9949,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.26,
|
| 42 |
+
"learning_rate": 9.490111779879622e-05,
|
| 43 |
+
"loss": 0.9739,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"learning_rate": 9.404127257093723e-05,
|
| 49 |
+
"loss": 0.9786,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.34,
|
| 54 |
+
"learning_rate": 9.318142734307826e-05,
|
| 55 |
+
"loss": 0.9689,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.39,
|
| 60 |
+
"learning_rate": 9.232158211521927e-05,
|
| 61 |
+
"loss": 0.9606,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.43,
|
| 66 |
+
"learning_rate": 9.146173688736028e-05,
|
| 67 |
+
"loss": 0.9493,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.47,
|
| 72 |
+
"learning_rate": 9.060189165950129e-05,
|
| 73 |
+
"loss": 0.9472,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.52,
|
| 78 |
+
"learning_rate": 8.974204643164231e-05,
|
| 79 |
+
"loss": 0.9372,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.56,
|
| 84 |
+
"learning_rate": 8.888220120378332e-05,
|
| 85 |
+
"loss": 0.9439,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"learning_rate": 8.802235597592435e-05,
|
| 91 |
+
"loss": 0.9453,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.64,
|
| 96 |
+
"learning_rate": 8.716251074806535e-05,
|
| 97 |
+
"loss": 0.9414,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.69,
|
| 102 |
+
"learning_rate": 8.630266552020637e-05,
|
| 103 |
+
"loss": 0.9247,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.73,
|
| 108 |
+
"learning_rate": 8.544282029234738e-05,
|
| 109 |
+
"loss": 0.9228,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.77,
|
| 114 |
+
"learning_rate": 8.45829750644884e-05,
|
| 115 |
+
"loss": 0.9209,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.82,
|
| 120 |
+
"learning_rate": 8.372312983662941e-05,
|
| 121 |
+
"loss": 0.9226,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.86,
|
| 126 |
+
"learning_rate": 8.286328460877043e-05,
|
| 127 |
+
"loss": 0.9172,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"learning_rate": 8.200343938091144e-05,
|
| 133 |
+
"loss": 0.8962,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.95,
|
| 138 |
+
"learning_rate": 8.114359415305245e-05,
|
| 139 |
+
"loss": 0.9071,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.99,
|
| 144 |
+
"learning_rate": 8.028374892519347e-05,
|
| 145 |
+
"loss": 0.9003,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.0,
|
| 150 |
+
"eval_loss": 0.8224605321884155,
|
| 151 |
+
"eval_runtime": 0.2074,
|
| 152 |
+
"eval_samples_per_second": 920.75,
|
| 153 |
+
"eval_steps_per_second": 14.462,
|
| 154 |
+
"step": 2326
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.03,
|
| 158 |
+
"learning_rate": 7.942390369733448e-05,
|
| 159 |
+
"loss": 0.8754,
|
| 160 |
+
"step": 2400
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.07,
|
| 164 |
+
"learning_rate": 7.856405846947549e-05,
|
| 165 |
+
"loss": 0.8697,
|
| 166 |
+
"step": 2500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.12,
|
| 170 |
+
"learning_rate": 7.77042132416165e-05,
|
| 171 |
+
"loss": 0.8656,
|
| 172 |
+
"step": 2600
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.16,
|
| 176 |
+
"learning_rate": 7.684436801375753e-05,
|
| 177 |
+
"loss": 0.8792,
|
| 178 |
+
"step": 2700
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.2,
|
| 182 |
+
"learning_rate": 7.598452278589854e-05,
|
| 183 |
+
"loss": 0.8648,
|
| 184 |
+
"step": 2800
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.25,
|
| 188 |
+
"learning_rate": 7.512467755803956e-05,
|
| 189 |
+
"loss": 0.8529,
|
| 190 |
+
"step": 2900
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.29,
|
| 194 |
+
"learning_rate": 7.426483233018057e-05,
|
| 195 |
+
"loss": 0.8492,
|
| 196 |
+
"step": 3000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.33,
|
| 200 |
+
"learning_rate": 7.340498710232158e-05,
|
| 201 |
+
"loss": 0.8615,
|
| 202 |
+
"step": 3100
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.38,
|
| 206 |
+
"learning_rate": 7.25451418744626e-05,
|
| 207 |
+
"loss": 0.8562,
|
| 208 |
+
"step": 3200
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.42,
|
| 212 |
+
"learning_rate": 7.168529664660362e-05,
|
| 213 |
+
"loss": 0.8594,
|
| 214 |
+
"step": 3300
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.46,
|
| 218 |
+
"learning_rate": 7.082545141874463e-05,
|
| 219 |
+
"loss": 0.8602,
|
| 220 |
+
"step": 3400
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.5,
|
| 224 |
+
"learning_rate": 6.996560619088564e-05,
|
| 225 |
+
"loss": 0.8553,
|
| 226 |
+
"step": 3500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.55,
|
| 230 |
+
"learning_rate": 6.910576096302665e-05,
|
| 231 |
+
"loss": 0.8616,
|
| 232 |
+
"step": 3600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.59,
|
| 236 |
+
"learning_rate": 6.824591573516768e-05,
|
| 237 |
+
"loss": 0.8533,
|
| 238 |
+
"step": 3700
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.63,
|
| 242 |
+
"learning_rate": 6.738607050730869e-05,
|
| 243 |
+
"loss": 0.845,
|
| 244 |
+
"step": 3800
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.68,
|
| 248 |
+
"learning_rate": 6.652622527944971e-05,
|
| 249 |
+
"loss": 0.8574,
|
| 250 |
+
"step": 3900
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.72,
|
| 254 |
+
"learning_rate": 6.566638005159072e-05,
|
| 255 |
+
"loss": 0.8518,
|
| 256 |
+
"step": 4000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.76,
|
| 260 |
+
"learning_rate": 6.480653482373173e-05,
|
| 261 |
+
"loss": 0.856,
|
| 262 |
+
"step": 4100
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.81,
|
| 266 |
+
"learning_rate": 6.394668959587274e-05,
|
| 267 |
+
"loss": 0.8442,
|
| 268 |
+
"step": 4200
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.85,
|
| 272 |
+
"learning_rate": 6.308684436801377e-05,
|
| 273 |
+
"loss": 0.8353,
|
| 274 |
+
"step": 4300
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.89,
|
| 278 |
+
"learning_rate": 6.222699914015478e-05,
|
| 279 |
+
"loss": 0.8407,
|
| 280 |
+
"step": 4400
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.93,
|
| 284 |
+
"learning_rate": 6.136715391229579e-05,
|
| 285 |
+
"loss": 0.8474,
|
| 286 |
+
"step": 4500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.98,
|
| 290 |
+
"learning_rate": 6.0507308684436805e-05,
|
| 291 |
+
"loss": 0.8506,
|
| 292 |
+
"step": 4600
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.0,
|
| 296 |
+
"eval_loss": 0.8073627352714539,
|
| 297 |
+
"eval_runtime": 0.2077,
|
| 298 |
+
"eval_samples_per_second": 919.421,
|
| 299 |
+
"eval_steps_per_second": 14.441,
|
| 300 |
+
"step": 4652
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.02,
|
| 304 |
+
"learning_rate": 5.964746345657782e-05,
|
| 305 |
+
"loss": 0.8277,
|
| 306 |
+
"step": 4700
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.06,
|
| 310 |
+
"learning_rate": 5.8787618228718834e-05,
|
| 311 |
+
"loss": 0.8104,
|
| 312 |
+
"step": 4800
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.11,
|
| 316 |
+
"learning_rate": 5.792777300085985e-05,
|
| 317 |
+
"loss": 0.8169,
|
| 318 |
+
"step": 4900
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.15,
|
| 322 |
+
"learning_rate": 5.706792777300086e-05,
|
| 323 |
+
"loss": 0.8068,
|
| 324 |
+
"step": 5000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.19,
|
| 328 |
+
"learning_rate": 5.620808254514188e-05,
|
| 329 |
+
"loss": 0.8026,
|
| 330 |
+
"step": 5100
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.24,
|
| 334 |
+
"learning_rate": 5.534823731728289e-05,
|
| 335 |
+
"loss": 0.8069,
|
| 336 |
+
"step": 5200
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.28,
|
| 340 |
+
"learning_rate": 5.44883920894239e-05,
|
| 341 |
+
"loss": 0.8118,
|
| 342 |
+
"step": 5300
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.32,
|
| 346 |
+
"learning_rate": 5.362854686156492e-05,
|
| 347 |
+
"loss": 0.8104,
|
| 348 |
+
"step": 5400
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.36,
|
| 352 |
+
"learning_rate": 5.276870163370593e-05,
|
| 353 |
+
"loss": 0.8071,
|
| 354 |
+
"step": 5500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.41,
|
| 358 |
+
"learning_rate": 5.190885640584695e-05,
|
| 359 |
+
"loss": 0.8068,
|
| 360 |
+
"step": 5600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.45,
|
| 364 |
+
"learning_rate": 5.104901117798796e-05,
|
| 365 |
+
"loss": 0.8033,
|
| 366 |
+
"step": 5700
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.49,
|
| 370 |
+
"learning_rate": 5.018916595012898e-05,
|
| 371 |
+
"loss": 0.8196,
|
| 372 |
+
"step": 5800
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.54,
|
| 376 |
+
"learning_rate": 4.932932072226999e-05,
|
| 377 |
+
"loss": 0.8016,
|
| 378 |
+
"step": 5900
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.58,
|
| 382 |
+
"learning_rate": 4.846947549441101e-05,
|
| 383 |
+
"loss": 0.7977,
|
| 384 |
+
"step": 6000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.62,
|
| 388 |
+
"learning_rate": 4.760963026655203e-05,
|
| 389 |
+
"loss": 0.8107,
|
| 390 |
+
"step": 6100
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.67,
|
| 394 |
+
"learning_rate": 4.674978503869304e-05,
|
| 395 |
+
"loss": 0.8128,
|
| 396 |
+
"step": 6200
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.71,
|
| 400 |
+
"learning_rate": 4.5889939810834055e-05,
|
| 401 |
+
"loss": 0.8018,
|
| 402 |
+
"step": 6300
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.75,
|
| 406 |
+
"learning_rate": 4.5030094582975066e-05,
|
| 407 |
+
"loss": 0.7966,
|
| 408 |
+
"step": 6400
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.79,
|
| 412 |
+
"learning_rate": 4.417024935511608e-05,
|
| 413 |
+
"loss": 0.8029,
|
| 414 |
+
"step": 6500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.84,
|
| 418 |
+
"learning_rate": 4.33104041272571e-05,
|
| 419 |
+
"loss": 0.7989,
|
| 420 |
+
"step": 6600
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.88,
|
| 424 |
+
"learning_rate": 4.245055889939811e-05,
|
| 425 |
+
"loss": 0.8102,
|
| 426 |
+
"step": 6700
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.92,
|
| 430 |
+
"learning_rate": 4.159071367153913e-05,
|
| 431 |
+
"loss": 0.7975,
|
| 432 |
+
"step": 6800
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.97,
|
| 436 |
+
"learning_rate": 4.073086844368014e-05,
|
| 437 |
+
"loss": 0.7997,
|
| 438 |
+
"step": 6900
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.0,
|
| 442 |
+
"eval_loss": 0.8013436794281006,
|
| 443 |
+
"eval_runtime": 0.2081,
|
| 444 |
+
"eval_samples_per_second": 917.66,
|
| 445 |
+
"eval_steps_per_second": 14.414,
|
| 446 |
+
"step": 6978
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.01,
|
| 450 |
+
"learning_rate": 3.987102321582115e-05,
|
| 451 |
+
"loss": 0.7997,
|
| 452 |
+
"step": 7000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.05,
|
| 456 |
+
"learning_rate": 3.901117798796217e-05,
|
| 457 |
+
"loss": 0.7764,
|
| 458 |
+
"step": 7100
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.1,
|
| 462 |
+
"learning_rate": 3.815133276010318e-05,
|
| 463 |
+
"loss": 0.7773,
|
| 464 |
+
"step": 7200
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.14,
|
| 468 |
+
"learning_rate": 3.7291487532244196e-05,
|
| 469 |
+
"loss": 0.7808,
|
| 470 |
+
"step": 7300
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.18,
|
| 474 |
+
"learning_rate": 3.643164230438521e-05,
|
| 475 |
+
"loss": 0.7676,
|
| 476 |
+
"step": 7400
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.22,
|
| 480 |
+
"learning_rate": 3.5571797076526224e-05,
|
| 481 |
+
"loss": 0.7632,
|
| 482 |
+
"step": 7500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.27,
|
| 486 |
+
"learning_rate": 3.471195184866724e-05,
|
| 487 |
+
"loss": 0.776,
|
| 488 |
+
"step": 7600
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.31,
|
| 492 |
+
"learning_rate": 3.385210662080825e-05,
|
| 493 |
+
"loss": 0.7804,
|
| 494 |
+
"step": 7700
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.35,
|
| 498 |
+
"learning_rate": 3.299226139294927e-05,
|
| 499 |
+
"loss": 0.781,
|
| 500 |
+
"step": 7800
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.4,
|
| 504 |
+
"learning_rate": 3.213241616509029e-05,
|
| 505 |
+
"loss": 0.7792,
|
| 506 |
+
"step": 7900
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.44,
|
| 510 |
+
"learning_rate": 3.12725709372313e-05,
|
| 511 |
+
"loss": 0.7799,
|
| 512 |
+
"step": 8000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.48,
|
| 516 |
+
"learning_rate": 3.0412725709372315e-05,
|
| 517 |
+
"loss": 0.7824,
|
| 518 |
+
"step": 8100
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.53,
|
| 522 |
+
"learning_rate": 2.955288048151333e-05,
|
| 523 |
+
"loss": 0.7701,
|
| 524 |
+
"step": 8200
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.57,
|
| 528 |
+
"learning_rate": 2.8693035253654343e-05,
|
| 529 |
+
"loss": 0.7752,
|
| 530 |
+
"step": 8300
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.61,
|
| 534 |
+
"learning_rate": 2.7833190025795357e-05,
|
| 535 |
+
"loss": 0.7668,
|
| 536 |
+
"step": 8400
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.65,
|
| 540 |
+
"learning_rate": 2.697334479793637e-05,
|
| 541 |
+
"loss": 0.7746,
|
| 542 |
+
"step": 8500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.7,
|
| 546 |
+
"learning_rate": 2.611349957007739e-05,
|
| 547 |
+
"loss": 0.7695,
|
| 548 |
+
"step": 8600
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.74,
|
| 552 |
+
"learning_rate": 2.5253654342218403e-05,
|
| 553 |
+
"loss": 0.7742,
|
| 554 |
+
"step": 8700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.78,
|
| 558 |
+
"learning_rate": 2.4393809114359417e-05,
|
| 559 |
+
"loss": 0.7833,
|
| 560 |
+
"step": 8800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.83,
|
| 564 |
+
"learning_rate": 2.353396388650043e-05,
|
| 565 |
+
"loss": 0.7753,
|
| 566 |
+
"step": 8900
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.87,
|
| 570 |
+
"learning_rate": 2.2674118658641445e-05,
|
| 571 |
+
"loss": 0.7688,
|
| 572 |
+
"step": 9000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.91,
|
| 576 |
+
"learning_rate": 2.1814273430782463e-05,
|
| 577 |
+
"loss": 0.773,
|
| 578 |
+
"step": 9100
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.96,
|
| 582 |
+
"learning_rate": 2.0954428202923474e-05,
|
| 583 |
+
"loss": 0.7658,
|
| 584 |
+
"step": 9200
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.0,
|
| 588 |
+
"learning_rate": 2.0094582975064488e-05,
|
| 589 |
+
"loss": 0.7776,
|
| 590 |
+
"step": 9300
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.0,
|
| 594 |
+
"eval_loss": 0.7975377440452576,
|
| 595 |
+
"eval_runtime": 0.2075,
|
| 596 |
+
"eval_samples_per_second": 920.648,
|
| 597 |
+
"eval_steps_per_second": 14.46,
|
| 598 |
+
"step": 9304
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 4.04,
|
| 602 |
+
"learning_rate": 1.9234737747205502e-05,
|
| 603 |
+
"loss": 0.7533,
|
| 604 |
+
"step": 9400
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.08,
|
| 608 |
+
"learning_rate": 1.837489251934652e-05,
|
| 609 |
+
"loss": 0.7556,
|
| 610 |
+
"step": 9500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.13,
|
| 614 |
+
"learning_rate": 1.7515047291487533e-05,
|
| 615 |
+
"loss": 0.7644,
|
| 616 |
+
"step": 9600
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.17,
|
| 620 |
+
"learning_rate": 1.6655202063628547e-05,
|
| 621 |
+
"loss": 0.7531,
|
| 622 |
+
"step": 9700
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 4.21,
|
| 626 |
+
"learning_rate": 1.579535683576956e-05,
|
| 627 |
+
"loss": 0.7543,
|
| 628 |
+
"step": 9800
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.26,
|
| 632 |
+
"learning_rate": 1.4935511607910577e-05,
|
| 633 |
+
"loss": 0.7586,
|
| 634 |
+
"step": 9900
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 4.3,
|
| 638 |
+
"learning_rate": 1.4075666380051591e-05,
|
| 639 |
+
"loss": 0.7643,
|
| 640 |
+
"step": 10000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.34,
|
| 644 |
+
"learning_rate": 1.3215821152192605e-05,
|
| 645 |
+
"loss": 0.757,
|
| 646 |
+
"step": 10100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.39,
|
| 650 |
+
"learning_rate": 1.2355975924333621e-05,
|
| 651 |
+
"loss": 0.7444,
|
| 652 |
+
"step": 10200
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 4.43,
|
| 656 |
+
"learning_rate": 1.1496130696474635e-05,
|
| 657 |
+
"loss": 0.7653,
|
| 658 |
+
"step": 10300
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 4.47,
|
| 662 |
+
"learning_rate": 1.063628546861565e-05,
|
| 663 |
+
"loss": 0.7693,
|
| 664 |
+
"step": 10400
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 4.51,
|
| 668 |
+
"learning_rate": 9.776440240756663e-06,
|
| 669 |
+
"loss": 0.7615,
|
| 670 |
+
"step": 10500
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 4.56,
|
| 674 |
+
"learning_rate": 8.91659501289768e-06,
|
| 675 |
+
"loss": 0.7517,
|
| 676 |
+
"step": 10600
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 4.6,
|
| 680 |
+
"learning_rate": 8.056749785038693e-06,
|
| 681 |
+
"loss": 0.7584,
|
| 682 |
+
"step": 10700
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.64,
|
| 686 |
+
"learning_rate": 7.196904557179708e-06,
|
| 687 |
+
"loss": 0.752,
|
| 688 |
+
"step": 10800
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.69,
|
| 692 |
+
"learning_rate": 6.337059329320723e-06,
|
| 693 |
+
"loss": 0.7509,
|
| 694 |
+
"step": 10900
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.73,
|
| 698 |
+
"learning_rate": 5.477214101461737e-06,
|
| 699 |
+
"loss": 0.7483,
|
| 700 |
+
"step": 11000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 4.77,
|
| 704 |
+
"learning_rate": 4.617368873602751e-06,
|
| 705 |
+
"loss": 0.755,
|
| 706 |
+
"step": 11100
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 4.82,
|
| 710 |
+
"learning_rate": 3.7575236457437662e-06,
|
| 711 |
+
"loss": 0.7585,
|
| 712 |
+
"step": 11200
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.86,
|
| 716 |
+
"learning_rate": 2.8976784178847807e-06,
|
| 717 |
+
"loss": 0.7537,
|
| 718 |
+
"step": 11300
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 4.9,
|
| 722 |
+
"learning_rate": 2.0378331900257957e-06,
|
| 723 |
+
"loss": 0.7511,
|
| 724 |
+
"step": 11400
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 4.94,
|
| 728 |
+
"learning_rate": 1.17798796216681e-06,
|
| 729 |
+
"loss": 0.7521,
|
| 730 |
+
"step": 11500
|
| 731 |
+
}
|
| 732 |
+
],
|
| 733 |
+
"max_steps": 11630,
|
| 734 |
+
"num_train_epochs": 5,
|
| 735 |
+
"total_flos": 6.009030844416e+16,
|
| 736 |
+
"trial_name": null,
|
| 737 |
+
"trial_params": null
|
| 738 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a39609c671e14f693a0ef1e953a6d760b0dfb7c8d32c59ef8482cb82d508b37a
|
| 3 |
+
size 3963
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|