Upload 18 files
Browse files- config.json +32 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +383 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"pad_token_id": 3,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_embd": 384,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 12,
|
| 18 |
+
"n_positions": 256,
|
| 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 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.43.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 12000
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 3,
|
| 5 |
+
"transformers_version": "4.43.4"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71e61d2705d4184d307e8fd884e5677c3a18c7960da940694fb0f805f6abaa76
|
| 3 |
+
size 104017304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56867779bd4a221e0b0fa2eab279afc7dc94f9897f2bb432e18334b5b57203c9
|
| 3 |
+
size 208128954
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d38f24d0fcf2527c9da2ea94c70c7e67f665d8ea54290ee6ae5bde1e4781ffe8
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b49c4b800043b05d1e2fa42803fb4921ea186b12ed4ce6416aac31cf1e955e26
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30770d8824a025e20fe44753be42c1eb0c72db3e392f2a64746a0e59e3c259ef
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f14d0f463239d393010dc2f7a2baa4a3401b97bac4f5ae0d4b16024cc283045
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c178b29d807a3639a6c43d2104c68d6ec1a9a1a76f27712d43f2516d99ad0bc
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e5fd66683e2743651618fb14b9cd5afca8e789bcb2bf5ba9c53d3930f1925db
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:686fed4dcddd0d1ab5b5924a8d1120c8b32dd1f50e24caf6134877812bd42615
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f083014cb24c93f6aca814fedc091758c04d2581bd029658b37f0a4f4ed90f4
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a38a6c75f6fec8488eb882905b588cd33da454bf2b48b1e2b6d68929753c5835
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|bos|>",
|
| 3 |
+
"eos_token": "<|eos|>",
|
| 4 |
+
"mask_token": "<|mask|>",
|
| 5 |
+
"pad_token": "<|pad|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<|mask|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|bos|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<|eos|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<|pad|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<|bos|>",
|
| 37 |
+
"clean_up_tokenization_spaces": true,
|
| 38 |
+
"eos_token": "<|eos|>",
|
| 39 |
+
"mask_token": "<|mask|>",
|
| 40 |
+
"model_max_length": 256,
|
| 41 |
+
"pad_token": "<|pad|>",
|
| 42 |
+
"return_tensors": "pt",
|
| 43 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 51.54639175257732,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 25000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0309278350515463,
|
| 13 |
+
"grad_norm": 4.000246524810791,
|
| 14 |
+
"learning_rate": 3.4364261168384886e-06,
|
| 15 |
+
"loss": 8.264,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0618556701030926,
|
| 20 |
+
"grad_norm": 2.342319965362549,
|
| 21 |
+
"learning_rate": 6.872852233676977e-06,
|
| 22 |
+
"loss": 6.6664,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0927835051546393,
|
| 27 |
+
"grad_norm": 2.5340118408203125,
|
| 28 |
+
"learning_rate": 1.0309278350515464e-05,
|
| 29 |
+
"loss": 5.3366,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.123711340206185,
|
| 34 |
+
"grad_norm": 2.5916709899902344,
|
| 35 |
+
"learning_rate": 1.3745704467353954e-05,
|
| 36 |
+
"loss": 4.4002,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.154639175257732,
|
| 41 |
+
"grad_norm": 3.448418378829956,
|
| 42 |
+
"learning_rate": 1.7182130584192442e-05,
|
| 43 |
+
"loss": 3.8367,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.185567010309279,
|
| 48 |
+
"grad_norm": 3.4657623767852783,
|
| 49 |
+
"learning_rate": 2.0618556701030927e-05,
|
| 50 |
+
"loss": 3.4293,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.216494845360825,
|
| 55 |
+
"grad_norm": 4.080520153045654,
|
| 56 |
+
"learning_rate": 2.4054982817869417e-05,
|
| 57 |
+
"loss": 3.1112,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.24742268041237,
|
| 62 |
+
"grad_norm": 3.7761707305908203,
|
| 63 |
+
"learning_rate": 2.749140893470791e-05,
|
| 64 |
+
"loss": 2.8723,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.278350515463918,
|
| 69 |
+
"grad_norm": 3.7703592777252197,
|
| 70 |
+
"learning_rate": 3.0927835051546395e-05,
|
| 71 |
+
"loss": 2.6786,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.309278350515465,
|
| 76 |
+
"grad_norm": 2.716610908508301,
|
| 77 |
+
"learning_rate": 3.4364261168384884e-05,
|
| 78 |
+
"loss": 2.5182,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.34020618556701,
|
| 83 |
+
"grad_norm": 3.0980777740478516,
|
| 84 |
+
"learning_rate": 3.7800687285223366e-05,
|
| 85 |
+
"loss": 2.388,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.371134020618557,
|
| 90 |
+
"grad_norm": 2.8109469413757324,
|
| 91 |
+
"learning_rate": 4.1237113402061855e-05,
|
| 92 |
+
"loss": 2.271,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.402061855670103,
|
| 97 |
+
"grad_norm": 2.512942314147949,
|
| 98 |
+
"learning_rate": 4.466666666666667e-05,
|
| 99 |
+
"loss": 2.1741,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 14.43298969072165,
|
| 104 |
+
"grad_norm": 2.585681200027466,
|
| 105 |
+
"learning_rate": 4.810309278350515e-05,
|
| 106 |
+
"loss": 2.0924,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.463917525773196,
|
| 111 |
+
"grad_norm": 2.4047884941101074,
|
| 112 |
+
"learning_rate": 5.153951890034364e-05,
|
| 113 |
+
"loss": 2.011,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 16.49484536082474,
|
| 118 |
+
"grad_norm": 2.4080662727355957,
|
| 119 |
+
"learning_rate": 5.497594501718213e-05,
|
| 120 |
+
"loss": 1.946,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.52577319587629,
|
| 125 |
+
"grad_norm": 2.2564289569854736,
|
| 126 |
+
"learning_rate": 5.840549828178694e-05,
|
| 127 |
+
"loss": 1.8899,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 18.556701030927837,
|
| 132 |
+
"grad_norm": 2.0903544425964355,
|
| 133 |
+
"learning_rate": 6.184192439862543e-05,
|
| 134 |
+
"loss": 1.8404,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 19.587628865979383,
|
| 139 |
+
"grad_norm": 2.0401394367218018,
|
| 140 |
+
"learning_rate": 6.527835051546391e-05,
|
| 141 |
+
"loss": 1.7894,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 20.61855670103093,
|
| 146 |
+
"grad_norm": 2.026660919189453,
|
| 147 |
+
"learning_rate": 6.87147766323024e-05,
|
| 148 |
+
"loss": 1.7505,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 21.649484536082475,
|
| 153 |
+
"grad_norm": 1.9435638189315796,
|
| 154 |
+
"learning_rate": 7.21512027491409e-05,
|
| 155 |
+
"loss": 1.7097,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 22.68041237113402,
|
| 160 |
+
"grad_norm": 1.9047859907150269,
|
| 161 |
+
"learning_rate": 7.558075601374571e-05,
|
| 162 |
+
"loss": 1.6748,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 23.711340206185568,
|
| 167 |
+
"grad_norm": 1.8212696313858032,
|
| 168 |
+
"learning_rate": 7.90171821305842e-05,
|
| 169 |
+
"loss": 1.64,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 24.742268041237114,
|
| 174 |
+
"grad_norm": 1.7629321813583374,
|
| 175 |
+
"learning_rate": 8.245360824742269e-05,
|
| 176 |
+
"loss": 1.6115,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 25.77319587628866,
|
| 181 |
+
"grad_norm": 1.7129898071289062,
|
| 182 |
+
"learning_rate": 8.589003436426117e-05,
|
| 183 |
+
"loss": 1.5824,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 26.804123711340207,
|
| 188 |
+
"grad_norm": 1.6478886604309082,
|
| 189 |
+
"learning_rate": 8.932646048109967e-05,
|
| 190 |
+
"loss": 1.5537,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 27.835051546391753,
|
| 195 |
+
"grad_norm": 1.6928553581237793,
|
| 196 |
+
"learning_rate": 9.276288659793815e-05,
|
| 197 |
+
"loss": 1.528,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 28.8659793814433,
|
| 202 |
+
"grad_norm": 1.5595742464065552,
|
| 203 |
+
"learning_rate": 9.619931271477663e-05,
|
| 204 |
+
"loss": 1.5037,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 29.896907216494846,
|
| 209 |
+
"grad_norm": 1.6010233163833618,
|
| 210 |
+
"learning_rate": 9.963573883161513e-05,
|
| 211 |
+
"loss": 1.4804,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 30.927835051546392,
|
| 216 |
+
"grad_norm": 1.4490132331848145,
|
| 217 |
+
"learning_rate": 9.99574236655172e-05,
|
| 218 |
+
"loss": 1.4564,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 31.95876288659794,
|
| 223 |
+
"grad_norm": 1.449069857597351,
|
| 224 |
+
"learning_rate": 9.980854570375779e-05,
|
| 225 |
+
"loss": 1.4322,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 32.98969072164948,
|
| 230 |
+
"grad_norm": 1.4955676794052124,
|
| 231 |
+
"learning_rate": 9.955306053101556e-05,
|
| 232 |
+
"loss": 1.4091,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 34.02061855670103,
|
| 237 |
+
"grad_norm": 1.4652965068817139,
|
| 238 |
+
"learning_rate": 9.919234343505417e-05,
|
| 239 |
+
"loss": 1.3867,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 35.05154639175258,
|
| 244 |
+
"grad_norm": 1.4383347034454346,
|
| 245 |
+
"learning_rate": 9.872572097155327e-05,
|
| 246 |
+
"loss": 1.367,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 36.08247422680412,
|
| 251 |
+
"grad_norm": 1.3232207298278809,
|
| 252 |
+
"learning_rate": 9.815480890990188e-05,
|
| 253 |
+
"loss": 1.3452,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 37.11340206185567,
|
| 258 |
+
"grad_norm": 1.3220405578613281,
|
| 259 |
+
"learning_rate": 9.748082919588761e-05,
|
| 260 |
+
"loss": 1.3265,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 38.144329896907216,
|
| 265 |
+
"grad_norm": 1.2943527698516846,
|
| 266 |
+
"learning_rate": 9.670522437509286e-05,
|
| 267 |
+
"loss": 1.3091,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 39.175257731958766,
|
| 272 |
+
"grad_norm": 1.3372294902801514,
|
| 273 |
+
"learning_rate": 9.582965450535715e-05,
|
| 274 |
+
"loss": 1.2913,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 40.20618556701031,
|
| 279 |
+
"grad_norm": 1.359191656112671,
|
| 280 |
+
"learning_rate": 9.485599360368925e-05,
|
| 281 |
+
"loss": 1.2745,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 41.23711340206186,
|
| 286 |
+
"grad_norm": 1.3238861560821533,
|
| 287 |
+
"learning_rate": 9.378632563523418e-05,
|
| 288 |
+
"loss": 1.2581,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 42.2680412371134,
|
| 293 |
+
"grad_norm": 1.311515212059021,
|
| 294 |
+
"learning_rate": 9.262535873205258e-05,
|
| 295 |
+
"loss": 1.2448,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 43.29896907216495,
|
| 300 |
+
"grad_norm": 1.3535444736480713,
|
| 301 |
+
"learning_rate": 9.137092541559738e-05,
|
| 302 |
+
"loss": 1.2271,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 44.329896907216494,
|
| 307 |
+
"grad_norm": 1.3142534494400024,
|
| 308 |
+
"learning_rate": 9.002794426238008e-05,
|
| 309 |
+
"loss": 1.2132,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 45.36082474226804,
|
| 314 |
+
"grad_norm": 1.3405091762542725,
|
| 315 |
+
"learning_rate": 8.859928970836587e-05,
|
| 316 |
+
"loss": 1.1984,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 46.391752577319586,
|
| 321 |
+
"grad_norm": 1.339012861251831,
|
| 322 |
+
"learning_rate": 8.709112242917366e-05,
|
| 323 |
+
"loss": 1.1846,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 47.422680412371136,
|
| 328 |
+
"grad_norm": 1.336722493171692,
|
| 329 |
+
"learning_rate": 8.550062673710893e-05,
|
| 330 |
+
"loss": 1.1725,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 48.45360824742268,
|
| 335 |
+
"grad_norm": 1.2952606678009033,
|
| 336 |
+
"learning_rate": 8.383414764197326e-05,
|
| 337 |
+
"loss": 1.1577,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 49.48453608247423,
|
| 342 |
+
"grad_norm": 1.2937185764312744,
|
| 343 |
+
"learning_rate": 8.209525197524074e-05,
|
| 344 |
+
"loss": 1.1451,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 50.51546391752577,
|
| 349 |
+
"grad_norm": 1.3922706842422485,
|
| 350 |
+
"learning_rate": 8.029134275478738e-05,
|
| 351 |
+
"loss": 1.1334,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 51.54639175257732,
|
| 356 |
+
"grad_norm": 1.2733055353164673,
|
| 357 |
+
"learning_rate": 7.841905215460069e-05,
|
| 358 |
+
"loss": 1.1203,
|
| 359 |
+
"step": 25000
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 500,
|
| 363 |
+
"max_steps": 48500,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 100,
|
| 366 |
+
"save_steps": 1000,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 1.046659236626432e+17,
|
| 380 |
+
"train_batch_size": 16,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d9b8ea95e96a9f656e1d9add4f99c81f65faaac191135bbbca51480d08eea0e
|
| 3 |
+
size 5304
|