First model version
Browse files- config.json +39 -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 +34 -0
- trainer_state.json +616 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sshleifer/tiny-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": 2,
|
| 16 |
+
"n_head": 2,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 2,
|
| 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": "4.25.1",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
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:f12c73d2dbcf4afe88abe24e15068670c968a0845c5ee50607cfd8403ef88905
|
| 3 |
+
size 837233
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:597bf4a84749b25ad5bc5d2636b35453b7589b5b4c3f659e4ccecbd8108312c6
|
| 3 |
+
size 2517777
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7df3ae8280aa859e20e462d2e92adcc38d7b859521fb27c1a8ea01768b5899af
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98d33ab1f4c30262c17c55f5a0f085179cc0b0238fa1bff3cb54e5ff678cf9f9
|
| 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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"errors": "replace",
|
| 21 |
+
"model_max_length": 1024,
|
| 22 |
+
"name_or_path": "sshleifer/tiny-gpt2",
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--sshleifer--tiny-gpt2/snapshots/5f91d94bd9cd7190a9f3216ff93cd1dd95f2c7be/special_tokens_map.json",
|
| 25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<|endoftext|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,616 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.013452914798206,
|
| 5 |
+
"global_step": 50000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 9.900000000000001e-05,
|
| 13 |
+
"loss": 10.747,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.28,
|
| 18 |
+
"learning_rate": 9.8e-05,
|
| 19 |
+
"loss": 10.5732,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.42,
|
| 24 |
+
"learning_rate": 9.7e-05,
|
| 25 |
+
"loss": 10.3685,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.56,
|
| 30 |
+
"learning_rate": 9.6e-05,
|
| 31 |
+
"loss": 10.1396,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.7,
|
| 36 |
+
"learning_rate": 9.5e-05,
|
| 37 |
+
"loss": 9.8958,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.84,
|
| 42 |
+
"learning_rate": 9.4e-05,
|
| 43 |
+
"loss": 9.6456,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.98,
|
| 48 |
+
"learning_rate": 9.300000000000001e-05,
|
| 49 |
+
"loss": 9.3974,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.12,
|
| 54 |
+
"learning_rate": 9.200000000000001e-05,
|
| 55 |
+
"loss": 9.155,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.26,
|
| 60 |
+
"learning_rate": 9.1e-05,
|
| 61 |
+
"loss": 8.9232,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.4,
|
| 66 |
+
"learning_rate": 9e-05,
|
| 67 |
+
"loss": 8.7067,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.54,
|
| 72 |
+
"learning_rate": 8.900000000000001e-05,
|
| 73 |
+
"loss": 8.5025,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.68,
|
| 78 |
+
"learning_rate": 8.800000000000001e-05,
|
| 79 |
+
"loss": 8.3157,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.82,
|
| 84 |
+
"learning_rate": 8.7e-05,
|
| 85 |
+
"loss": 8.1445,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.96,
|
| 90 |
+
"learning_rate": 8.6e-05,
|
| 91 |
+
"loss": 7.9859,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.1,
|
| 96 |
+
"learning_rate": 8.5e-05,
|
| 97 |
+
"loss": 7.8496,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.24,
|
| 102 |
+
"learning_rate": 8.4e-05,
|
| 103 |
+
"loss": 7.7338,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.38,
|
| 108 |
+
"learning_rate": 8.3e-05,
|
| 109 |
+
"loss": 7.6332,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.52,
|
| 114 |
+
"learning_rate": 8.2e-05,
|
| 115 |
+
"loss": 7.5624,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.66,
|
| 120 |
+
"learning_rate": 8.1e-05,
|
| 121 |
+
"loss": 7.5056,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.8,
|
| 126 |
+
"learning_rate": 8e-05,
|
| 127 |
+
"loss": 7.4691,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.94,
|
| 132 |
+
"learning_rate": 7.900000000000001e-05,
|
| 133 |
+
"loss": 7.446,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.08,
|
| 138 |
+
"learning_rate": 7.800000000000001e-05,
|
| 139 |
+
"loss": 7.4321,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.22,
|
| 144 |
+
"learning_rate": 7.7e-05,
|
| 145 |
+
"loss": 7.423,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.36,
|
| 150 |
+
"learning_rate": 7.6e-05,
|
| 151 |
+
"loss": 7.417,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.5,
|
| 156 |
+
"learning_rate": 7.500000000000001e-05,
|
| 157 |
+
"loss": 7.4149,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.64,
|
| 162 |
+
"learning_rate": 7.4e-05,
|
| 163 |
+
"loss": 7.4151,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.78,
|
| 168 |
+
"learning_rate": 7.3e-05,
|
| 169 |
+
"loss": 7.4099,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.92,
|
| 174 |
+
"learning_rate": 7.2e-05,
|
| 175 |
+
"loss": 7.4135,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.06,
|
| 180 |
+
"learning_rate": 7.1e-05,
|
| 181 |
+
"loss": 7.4121,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.2,
|
| 186 |
+
"learning_rate": 7e-05,
|
| 187 |
+
"loss": 7.4121,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.34,
|
| 192 |
+
"learning_rate": 6.9e-05,
|
| 193 |
+
"loss": 7.4121,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.48,
|
| 198 |
+
"learning_rate": 6.800000000000001e-05,
|
| 199 |
+
"loss": 7.4097,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.62,
|
| 204 |
+
"learning_rate": 6.7e-05,
|
| 205 |
+
"loss": 7.4111,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.76,
|
| 210 |
+
"learning_rate": 6.6e-05,
|
| 211 |
+
"loss": 7.4112,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.9,
|
| 216 |
+
"learning_rate": 6.500000000000001e-05,
|
| 217 |
+
"loss": 7.4113,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.04,
|
| 222 |
+
"learning_rate": 6.400000000000001e-05,
|
| 223 |
+
"loss": 7.4102,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.18,
|
| 228 |
+
"learning_rate": 6.3e-05,
|
| 229 |
+
"loss": 7.4101,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.33,
|
| 234 |
+
"learning_rate": 6.2e-05,
|
| 235 |
+
"loss": 7.4114,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.47,
|
| 240 |
+
"learning_rate": 6.1e-05,
|
| 241 |
+
"loss": 7.4093,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 5.61,
|
| 246 |
+
"learning_rate": 6e-05,
|
| 247 |
+
"loss": 7.412,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.75,
|
| 252 |
+
"learning_rate": 5.9e-05,
|
| 253 |
+
"loss": 7.4086,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.89,
|
| 258 |
+
"learning_rate": 5.8e-05,
|
| 259 |
+
"loss": 7.4081,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.03,
|
| 264 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 265 |
+
"loss": 7.4085,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.17,
|
| 270 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 271 |
+
"loss": 7.4107,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 6.31,
|
| 276 |
+
"learning_rate": 5.500000000000001e-05,
|
| 277 |
+
"loss": 7.4079,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.45,
|
| 282 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 283 |
+
"loss": 7.4104,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.59,
|
| 288 |
+
"learning_rate": 5.300000000000001e-05,
|
| 289 |
+
"loss": 7.4088,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.73,
|
| 294 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 295 |
+
"loss": 7.4087,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.87,
|
| 300 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 301 |
+
"loss": 7.4079,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 7.01,
|
| 306 |
+
"learning_rate": 5e-05,
|
| 307 |
+
"loss": 7.4094,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 7.15,
|
| 312 |
+
"learning_rate": 4.9e-05,
|
| 313 |
+
"loss": 7.4098,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 7.29,
|
| 318 |
+
"learning_rate": 4.8e-05,
|
| 319 |
+
"loss": 7.4102,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.43,
|
| 324 |
+
"learning_rate": 4.7e-05,
|
| 325 |
+
"loss": 7.4107,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.57,
|
| 330 |
+
"learning_rate": 4.600000000000001e-05,
|
| 331 |
+
"loss": 7.4099,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.71,
|
| 336 |
+
"learning_rate": 4.5e-05,
|
| 337 |
+
"loss": 7.4086,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.85,
|
| 342 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 343 |
+
"loss": 7.4061,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 7.99,
|
| 348 |
+
"learning_rate": 4.3e-05,
|
| 349 |
+
"loss": 7.407,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 8.13,
|
| 354 |
+
"learning_rate": 4.2e-05,
|
| 355 |
+
"loss": 7.4098,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 8.27,
|
| 360 |
+
"learning_rate": 4.1e-05,
|
| 361 |
+
"loss": 7.4087,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 8.41,
|
| 366 |
+
"learning_rate": 4e-05,
|
| 367 |
+
"loss": 7.4079,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 8.55,
|
| 372 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 373 |
+
"loss": 7.4076,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.69,
|
| 378 |
+
"learning_rate": 3.8e-05,
|
| 379 |
+
"loss": 7.4066,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.83,
|
| 384 |
+
"learning_rate": 3.7e-05,
|
| 385 |
+
"loss": 7.4105,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 8.97,
|
| 390 |
+
"learning_rate": 3.6e-05,
|
| 391 |
+
"loss": 7.4094,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 9.11,
|
| 396 |
+
"learning_rate": 3.5e-05,
|
| 397 |
+
"loss": 7.4101,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 9.25,
|
| 402 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 403 |
+
"loss": 7.4094,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 9.39,
|
| 408 |
+
"learning_rate": 3.3e-05,
|
| 409 |
+
"loss": 7.4067,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 9.53,
|
| 414 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 415 |
+
"loss": 7.4103,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.67,
|
| 420 |
+
"learning_rate": 3.1e-05,
|
| 421 |
+
"loss": 7.4074,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.81,
|
| 426 |
+
"learning_rate": 3e-05,
|
| 427 |
+
"loss": 7.4091,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 9.95,
|
| 432 |
+
"learning_rate": 2.9e-05,
|
| 433 |
+
"loss": 7.409,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 10.09,
|
| 438 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 439 |
+
"loss": 7.4096,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 10.23,
|
| 444 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 445 |
+
"loss": 7.4091,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 10.37,
|
| 450 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 451 |
+
"loss": 7.4053,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.51,
|
| 456 |
+
"learning_rate": 2.5e-05,
|
| 457 |
+
"loss": 7.4117,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 10.65,
|
| 462 |
+
"learning_rate": 2.4e-05,
|
| 463 |
+
"loss": 7.4081,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 10.79,
|
| 468 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 469 |
+
"loss": 7.4066,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 10.93,
|
| 474 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 475 |
+
"loss": 7.4096,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 11.07,
|
| 480 |
+
"learning_rate": 2.1e-05,
|
| 481 |
+
"loss": 7.4072,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 11.21,
|
| 486 |
+
"learning_rate": 2e-05,
|
| 487 |
+
"loss": 7.4095,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 11.35,
|
| 492 |
+
"learning_rate": 1.9e-05,
|
| 493 |
+
"loss": 7.4074,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 11.49,
|
| 498 |
+
"learning_rate": 1.8e-05,
|
| 499 |
+
"loss": 7.4101,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 11.63,
|
| 504 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 505 |
+
"loss": 7.4106,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 11.77,
|
| 510 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 511 |
+
"loss": 7.4078,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 11.91,
|
| 516 |
+
"learning_rate": 1.5e-05,
|
| 517 |
+
"loss": 7.4063,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 12.05,
|
| 522 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 523 |
+
"loss": 7.4094,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 12.19,
|
| 528 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 529 |
+
"loss": 7.4071,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 12.33,
|
| 534 |
+
"learning_rate": 1.2e-05,
|
| 535 |
+
"loss": 7.407,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 12.47,
|
| 540 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 541 |
+
"loss": 7.4092,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 12.61,
|
| 546 |
+
"learning_rate": 1e-05,
|
| 547 |
+
"loss": 7.4088,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 12.75,
|
| 552 |
+
"learning_rate": 9e-06,
|
| 553 |
+
"loss": 7.4092,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 12.89,
|
| 558 |
+
"learning_rate": 8.000000000000001e-06,
|
| 559 |
+
"loss": 7.4099,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 13.03,
|
| 564 |
+
"learning_rate": 7.000000000000001e-06,
|
| 565 |
+
"loss": 7.4066,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 13.17,
|
| 570 |
+
"learning_rate": 6e-06,
|
| 571 |
+
"loss": 7.4069,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 13.31,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 7.4079,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 13.45,
|
| 582 |
+
"learning_rate": 4.000000000000001e-06,
|
| 583 |
+
"loss": 7.4085,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 13.59,
|
| 588 |
+
"learning_rate": 3e-06,
|
| 589 |
+
"loss": 7.4073,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 13.73,
|
| 594 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 595 |
+
"loss": 7.4084,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 13.87,
|
| 600 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 601 |
+
"loss": 7.4107,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 14.01,
|
| 606 |
+
"learning_rate": 0.0,
|
| 607 |
+
"loss": 7.4089,
|
| 608 |
+
"step": 50000
|
| 609 |
+
}
|
| 610 |
+
],
|
| 611 |
+
"max_steps": 50000,
|
| 612 |
+
"num_train_epochs": 15,
|
| 613 |
+
"total_flos": 1493867790336.0,
|
| 614 |
+
"trial_name": null,
|
| 615 |
+
"trial_params": null
|
| 616 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:744c8b48ec3c78c469c26dc0c4d3a56c19e9bc5f491ebbdeded3f8d8cdddc06f
|
| 3 |
+
size 3387
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|