Upload folder using huggingface_hub
Browse files- added_tokens.json +7 -0
- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +60 -0
- tokenizer.json +0 -0
- tokenizer_config.json +69 -0
- trainer_state.json +449 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endofline|>": 50259,
|
| 3 |
+
"<|endofsong|>": 50261,
|
| 4 |
+
"<|pad|>": 50257,
|
| 5 |
+
"<|startofline|>": 50258,
|
| 6 |
+
"<|startofsong|>": 50260
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 768,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 12,
|
| 18 |
+
"n_positions": 1024,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"text-generation": {
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"max_length": 50
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.51.0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50262
|
| 38 |
+
}
|
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": "4.51.0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5c0caa5b22fe458e8a2043ecbb3fcaead2ef94184d368a5a08079fa20a86301
|
| 3 |
+
size 497789568
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41bd3f9bad85eb208c4251cc31c23675a54cce589c7fceb72ffd944b138d0b48
|
| 3 |
+
size 995673018
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbff58bc3d4797a1329aa4a9e623f270d002c625cb63efe7325288189b65fc10
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b20682d68cd70b8b0b208c3bd5f62edfdf7322c345d5f8fb0fc9912581d14875
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eedf8430982bdd1e0d375cd000173068452f11c280e11e4047056f66bab10d96
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|startofline|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|endofline|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|startofsong|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|endofsong|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"bos_token": {
|
| 33 |
+
"content": "<|endoftext|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": true,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"eos_token": {
|
| 40 |
+
"content": "<|endoftext|>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"pad_token": {
|
| 47 |
+
"content": "<|pad|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
},
|
| 53 |
+
"unk_token": {
|
| 54 |
+
"content": "<|endoftext|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false
|
| 59 |
+
}
|
| 60 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"50257": {
|
| 14 |
+
"content": "<|pad|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"50258": {
|
| 22 |
+
"content": "<|startofline|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"50259": {
|
| 30 |
+
"content": "<|endofline|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"50260": {
|
| 38 |
+
"content": "<|startofsong|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"50261": {
|
| 46 |
+
"content": "<|endofsong|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
"additional_special_tokens": [
|
| 55 |
+
"<|startofline|>",
|
| 56 |
+
"<|endofline|>",
|
| 57 |
+
"<|startofsong|>",
|
| 58 |
+
"<|endofsong|>"
|
| 59 |
+
],
|
| 60 |
+
"bos_token": "<|endoftext|>",
|
| 61 |
+
"clean_up_tokenization_spaces": true,
|
| 62 |
+
"eos_token": "<|endoftext|>",
|
| 63 |
+
"errors": "replace",
|
| 64 |
+
"extra_special_tokens": {},
|
| 65 |
+
"model_max_length": 1024,
|
| 66 |
+
"pad_token": "<|pad|>",
|
| 67 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 68 |
+
"unk_token": "<|endoftext|>"
|
| 69 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,449 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4500,
|
| 3 |
+
"best_metric": 4.143945693969727,
|
| 4 |
+
"best_model_checkpoint": "checkpoints/checkpoint-4500",
|
| 5 |
+
"epoch": 4.999113362887904,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4930,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.1013299556681444,
|
| 14 |
+
"grad_norm": 53.731651306152344,
|
| 15 |
+
"learning_rate": 9.600000000000001e-06,
|
| 16 |
+
"loss": 8.2301,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.2026599113362888,
|
| 21 |
+
"grad_norm": 60.03353500366211,
|
| 22 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 23 |
+
"loss": 7.2402,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.3039898670044332,
|
| 28 |
+
"grad_norm": 56.0938606262207,
|
| 29 |
+
"learning_rate": 2.96e-05,
|
| 30 |
+
"loss": 6.1337,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.4053198226725776,
|
| 35 |
+
"grad_norm": 7.5981974601745605,
|
| 36 |
+
"learning_rate": 3.960000000000001e-05,
|
| 37 |
+
"loss": 5.0118,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.506649778340722,
|
| 42 |
+
"grad_norm": 3.361119270324707,
|
| 43 |
+
"learning_rate": 4.96e-05,
|
| 44 |
+
"loss": 4.6704,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.506649778340722,
|
| 49 |
+
"eval_loss": 4.494482517242432,
|
| 50 |
+
"eval_runtime": 61.163,
|
| 51 |
+
"eval_samples_per_second": 57.371,
|
| 52 |
+
"eval_steps_per_second": 14.355,
|
| 53 |
+
"step": 500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.6079797340088664,
|
| 57 |
+
"grad_norm": 2.7135744094848633,
|
| 58 |
+
"learning_rate": 4.891647855530474e-05,
|
| 59 |
+
"loss": 4.642,
|
| 60 |
+
"step": 600
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.7093096896770108,
|
| 64 |
+
"grad_norm": 3.0142900943756104,
|
| 65 |
+
"learning_rate": 4.7787810383747176e-05,
|
| 66 |
+
"loss": 4.5258,
|
| 67 |
+
"step": 700
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.8106396453451552,
|
| 71 |
+
"grad_norm": 2.4529480934143066,
|
| 72 |
+
"learning_rate": 4.665914221218962e-05,
|
| 73 |
+
"loss": 4.5282,
|
| 74 |
+
"step": 800
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.9119696010132996,
|
| 78 |
+
"grad_norm": 2.8447184562683105,
|
| 79 |
+
"learning_rate": 4.553047404063205e-05,
|
| 80 |
+
"loss": 4.4796,
|
| 81 |
+
"step": 900
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0141861937935401,
|
| 85 |
+
"grad_norm": 2.4824981689453125,
|
| 86 |
+
"learning_rate": 4.440180586907449e-05,
|
| 87 |
+
"loss": 4.5166,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0141861937935401,
|
| 92 |
+
"eval_loss": 4.318243980407715,
|
| 93 |
+
"eval_runtime": 61.4718,
|
| 94 |
+
"eval_samples_per_second": 57.083,
|
| 95 |
+
"eval_steps_per_second": 14.283,
|
| 96 |
+
"step": 1000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.1155161494616845,
|
| 100 |
+
"grad_norm": 2.3135533332824707,
|
| 101 |
+
"learning_rate": 4.327313769751693e-05,
|
| 102 |
+
"loss": 4.41,
|
| 103 |
+
"step": 1100
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.216846105129829,
|
| 107 |
+
"grad_norm": 2.297306537628174,
|
| 108 |
+
"learning_rate": 4.214446952595937e-05,
|
| 109 |
+
"loss": 4.429,
|
| 110 |
+
"step": 1200
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.3181760607979733,
|
| 114 |
+
"grad_norm": 2.43269944190979,
|
| 115 |
+
"learning_rate": 4.101580135440181e-05,
|
| 116 |
+
"loss": 4.3426,
|
| 117 |
+
"step": 1300
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.4195060164661177,
|
| 121 |
+
"grad_norm": 2.2192583084106445,
|
| 122 |
+
"learning_rate": 3.988713318284424e-05,
|
| 123 |
+
"loss": 4.3375,
|
| 124 |
+
"step": 1400
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.5208359721342621,
|
| 128 |
+
"grad_norm": 2.4804940223693848,
|
| 129 |
+
"learning_rate": 3.875846501128668e-05,
|
| 130 |
+
"loss": 4.3412,
|
| 131 |
+
"step": 1500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.5208359721342621,
|
| 135 |
+
"eval_loss": 4.256350994110107,
|
| 136 |
+
"eval_runtime": 61.1509,
|
| 137 |
+
"eval_samples_per_second": 57.383,
|
| 138 |
+
"eval_steps_per_second": 14.358,
|
| 139 |
+
"step": 1500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.6221659278024065,
|
| 143 |
+
"grad_norm": 2.0531516075134277,
|
| 144 |
+
"learning_rate": 3.762979683972912e-05,
|
| 145 |
+
"loss": 4.3421,
|
| 146 |
+
"step": 1600
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.723495883470551,
|
| 150 |
+
"grad_norm": 2.3188295364379883,
|
| 151 |
+
"learning_rate": 3.650112866817156e-05,
|
| 152 |
+
"loss": 4.3078,
|
| 153 |
+
"step": 1700
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.8248258391386953,
|
| 157 |
+
"grad_norm": 2.002288341522217,
|
| 158 |
+
"learning_rate": 3.5372460496614e-05,
|
| 159 |
+
"loss": 4.3323,
|
| 160 |
+
"step": 1800
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.9261557948068397,
|
| 164 |
+
"grad_norm": 2.439591646194458,
|
| 165 |
+
"learning_rate": 3.424379232505643e-05,
|
| 166 |
+
"loss": 4.3238,
|
| 167 |
+
"step": 1900
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.0283723875870803,
|
| 171 |
+
"grad_norm": 2.314893960952759,
|
| 172 |
+
"learning_rate": 3.3115124153498873e-05,
|
| 173 |
+
"loss": 4.3637,
|
| 174 |
+
"step": 2000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.0283723875870803,
|
| 178 |
+
"eval_loss": 4.224379539489746,
|
| 179 |
+
"eval_runtime": 61.2066,
|
| 180 |
+
"eval_samples_per_second": 57.33,
|
| 181 |
+
"eval_steps_per_second": 14.345,
|
| 182 |
+
"step": 2000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.1297023432552247,
|
| 186 |
+
"grad_norm": 2.339419364929199,
|
| 187 |
+
"learning_rate": 3.198645598194131e-05,
|
| 188 |
+
"loss": 4.2702,
|
| 189 |
+
"step": 2100
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.231032298923369,
|
| 193 |
+
"grad_norm": 2.3098413944244385,
|
| 194 |
+
"learning_rate": 3.085778781038375e-05,
|
| 195 |
+
"loss": 4.2843,
|
| 196 |
+
"step": 2200
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.3323622545915135,
|
| 200 |
+
"grad_norm": 2.1247897148132324,
|
| 201 |
+
"learning_rate": 2.9729119638826186e-05,
|
| 202 |
+
"loss": 4.2886,
|
| 203 |
+
"step": 2300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.433692210259658,
|
| 207 |
+
"grad_norm": 2.2844860553741455,
|
| 208 |
+
"learning_rate": 2.8600451467268623e-05,
|
| 209 |
+
"loss": 4.2878,
|
| 210 |
+
"step": 2400
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.5350221659278023,
|
| 214 |
+
"grad_norm": 2.0234220027923584,
|
| 215 |
+
"learning_rate": 2.747178329571106e-05,
|
| 216 |
+
"loss": 4.2488,
|
| 217 |
+
"step": 2500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.5350221659278023,
|
| 221 |
+
"eval_loss": 4.1915154457092285,
|
| 222 |
+
"eval_runtime": 61.5807,
|
| 223 |
+
"eval_samples_per_second": 56.982,
|
| 224 |
+
"eval_steps_per_second": 14.258,
|
| 225 |
+
"step": 2500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.6363521215959467,
|
| 229 |
+
"grad_norm": 2.2979116439819336,
|
| 230 |
+
"learning_rate": 2.63431151241535e-05,
|
| 231 |
+
"loss": 4.2168,
|
| 232 |
+
"step": 2600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.737682077264091,
|
| 236 |
+
"grad_norm": 2.3979334831237793,
|
| 237 |
+
"learning_rate": 2.521444695259594e-05,
|
| 238 |
+
"loss": 4.2475,
|
| 239 |
+
"step": 2700
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.8390120329322355,
|
| 243 |
+
"grad_norm": 2.207998037338257,
|
| 244 |
+
"learning_rate": 2.4085778781038376e-05,
|
| 245 |
+
"loss": 4.2249,
|
| 246 |
+
"step": 2800
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.94034198860038,
|
| 250 |
+
"grad_norm": 2.1592469215393066,
|
| 251 |
+
"learning_rate": 2.2957110609480814e-05,
|
| 252 |
+
"loss": 4.2234,
|
| 253 |
+
"step": 2900
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.0425585813806206,
|
| 257 |
+
"grad_norm": 2.058875560760498,
|
| 258 |
+
"learning_rate": 2.182844243792325e-05,
|
| 259 |
+
"loss": 4.2611,
|
| 260 |
+
"step": 3000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0425585813806206,
|
| 264 |
+
"eval_loss": 4.1719160079956055,
|
| 265 |
+
"eval_runtime": 61.4253,
|
| 266 |
+
"eval_samples_per_second": 57.126,
|
| 267 |
+
"eval_steps_per_second": 14.294,
|
| 268 |
+
"step": 3000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.143888537048765,
|
| 272 |
+
"grad_norm": 2.292440414428711,
|
| 273 |
+
"learning_rate": 2.069977426636569e-05,
|
| 274 |
+
"loss": 4.1453,
|
| 275 |
+
"step": 3100
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.2452184927169094,
|
| 279 |
+
"grad_norm": 2.633338451385498,
|
| 280 |
+
"learning_rate": 1.957110609480813e-05,
|
| 281 |
+
"loss": 4.182,
|
| 282 |
+
"step": 3200
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.346548448385054,
|
| 286 |
+
"grad_norm": 2.1391022205352783,
|
| 287 |
+
"learning_rate": 1.8442437923250567e-05,
|
| 288 |
+
"loss": 4.1905,
|
| 289 |
+
"step": 3300
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.4478784040531982,
|
| 293 |
+
"grad_norm": 2.2888920307159424,
|
| 294 |
+
"learning_rate": 1.7313769751693004e-05,
|
| 295 |
+
"loss": 4.1835,
|
| 296 |
+
"step": 3400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.5492083597213426,
|
| 300 |
+
"grad_norm": 2.186450481414795,
|
| 301 |
+
"learning_rate": 1.6185101580135442e-05,
|
| 302 |
+
"loss": 4.2083,
|
| 303 |
+
"step": 3500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.5492083597213426,
|
| 307 |
+
"eval_loss": 4.161413192749023,
|
| 308 |
+
"eval_runtime": 61.3496,
|
| 309 |
+
"eval_samples_per_second": 57.197,
|
| 310 |
+
"eval_steps_per_second": 14.311,
|
| 311 |
+
"step": 3500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.650538315389487,
|
| 315 |
+
"grad_norm": 2.072542190551758,
|
| 316 |
+
"learning_rate": 1.5056433408577881e-05,
|
| 317 |
+
"loss": 4.2393,
|
| 318 |
+
"step": 3600
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.7518682710576314,
|
| 322 |
+
"grad_norm": 2.1177375316619873,
|
| 323 |
+
"learning_rate": 1.3927765237020315e-05,
|
| 324 |
+
"loss": 4.2243,
|
| 325 |
+
"step": 3700
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.853198226725776,
|
| 329 |
+
"grad_norm": 2.2772135734558105,
|
| 330 |
+
"learning_rate": 1.2799097065462754e-05,
|
| 331 |
+
"loss": 4.2019,
|
| 332 |
+
"step": 3800
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.9545281823939202,
|
| 336 |
+
"grad_norm": 2.0697269439697266,
|
| 337 |
+
"learning_rate": 1.1670428893905193e-05,
|
| 338 |
+
"loss": 4.2285,
|
| 339 |
+
"step": 3900
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.0567447751741605,
|
| 343 |
+
"grad_norm": 2.685513734817505,
|
| 344 |
+
"learning_rate": 1.054176072234763e-05,
|
| 345 |
+
"loss": 4.2405,
|
| 346 |
+
"step": 4000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.0567447751741605,
|
| 350 |
+
"eval_loss": 4.150519847869873,
|
| 351 |
+
"eval_runtime": 61.2476,
|
| 352 |
+
"eval_samples_per_second": 57.292,
|
| 353 |
+
"eval_steps_per_second": 14.335,
|
| 354 |
+
"step": 4000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.158074730842305,
|
| 358 |
+
"grad_norm": 2.0102524757385254,
|
| 359 |
+
"learning_rate": 9.413092550790068e-06,
|
| 360 |
+
"loss": 4.1516,
|
| 361 |
+
"step": 4100
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.259404686510449,
|
| 365 |
+
"grad_norm": 2.008261203765869,
|
| 366 |
+
"learning_rate": 8.284424379232506e-06,
|
| 367 |
+
"loss": 4.145,
|
| 368 |
+
"step": 4200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.360734642178594,
|
| 372 |
+
"grad_norm": 2.0506038665771484,
|
| 373 |
+
"learning_rate": 7.155756207674943e-06,
|
| 374 |
+
"loss": 4.1747,
|
| 375 |
+
"step": 4300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.462064597846738,
|
| 379 |
+
"grad_norm": 2.1455721855163574,
|
| 380 |
+
"learning_rate": 6.0270880361173815e-06,
|
| 381 |
+
"loss": 4.1857,
|
| 382 |
+
"step": 4400
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 4.5633945535148825,
|
| 386 |
+
"grad_norm": 2.101816177368164,
|
| 387 |
+
"learning_rate": 4.89841986455982e-06,
|
| 388 |
+
"loss": 4.1556,
|
| 389 |
+
"step": 4500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 4.5633945535148825,
|
| 393 |
+
"eval_loss": 4.143945693969727,
|
| 394 |
+
"eval_runtime": 61.2556,
|
| 395 |
+
"eval_samples_per_second": 57.285,
|
| 396 |
+
"eval_steps_per_second": 14.333,
|
| 397 |
+
"step": 4500
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 4.664724509183027,
|
| 401 |
+
"grad_norm": 2.203230619430542,
|
| 402 |
+
"learning_rate": 3.7697516930022577e-06,
|
| 403 |
+
"loss": 4.1613,
|
| 404 |
+
"step": 4600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.766054464851171,
|
| 408 |
+
"grad_norm": 1.9926562309265137,
|
| 409 |
+
"learning_rate": 2.6410835214446955e-06,
|
| 410 |
+
"loss": 4.2135,
|
| 411 |
+
"step": 4700
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.867384420519316,
|
| 415 |
+
"grad_norm": 2.189359426498413,
|
| 416 |
+
"learning_rate": 1.5124153498871334e-06,
|
| 417 |
+
"loss": 4.1631,
|
| 418 |
+
"step": 4800
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 4.96871437618746,
|
| 422 |
+
"grad_norm": 2.3265554904937744,
|
| 423 |
+
"learning_rate": 3.837471783295711e-07,
|
| 424 |
+
"loss": 4.1366,
|
| 425 |
+
"step": 4900
|
| 426 |
+
}
|
| 427 |
+
],
|
| 428 |
+
"logging_steps": 100,
|
| 429 |
+
"max_steps": 4930,
|
| 430 |
+
"num_input_tokens_seen": 0,
|
| 431 |
+
"num_train_epochs": 5,
|
| 432 |
+
"save_steps": 500,
|
| 433 |
+
"stateful_callbacks": {
|
| 434 |
+
"TrainerControl": {
|
| 435 |
+
"args": {
|
| 436 |
+
"should_epoch_stop": false,
|
| 437 |
+
"should_evaluate": false,
|
| 438 |
+
"should_log": false,
|
| 439 |
+
"should_save": true,
|
| 440 |
+
"should_training_stop": true
|
| 441 |
+
},
|
| 442 |
+
"attributes": {}
|
| 443 |
+
}
|
| 444 |
+
},
|
| 445 |
+
"total_flos": 8.2088082473472e+16,
|
| 446 |
+
"train_batch_size": 4,
|
| 447 |
+
"trial_name": null,
|
| 448 |
+
"trial_params": null
|
| 449 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5092045063b6078b36cb9bc3ca73af025833eebd5942cbab8ac1893d81ff270
|
| 3 |
+
size 5240
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|