Commit
•
631fbd6
1
Parent(s):
ae48852
Upload 8 files
Browse files- checkpoint-25000/config.json +31 -0
- checkpoint-25000/generation_config.json +7 -0
- checkpoint-25000/optimizer.pt +3 -0
- checkpoint-25000/pytorch_model.bin +3 -0
- checkpoint-25000/rng_state.pth +3 -0
- checkpoint-25000/scheduler.pt +3 -0
- checkpoint-25000/trainer_state.json +846 -0
- checkpoint-25000/training_args.bin +3 -0
checkpoint-25000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./models/checkpoint-22500",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 1024,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 8,
|
| 20 |
+
"num_heads": 6,
|
| 21 |
+
"num_layers": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_max_distance": 128,
|
| 24 |
+
"relative_attention_num_buckets": 32,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"tokenizer_class": "T5Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.28.0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250112
|
| 31 |
+
}
|
checkpoint-25000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0"
|
| 7 |
+
}
|
checkpoint-25000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4b191bae19af3c9197ab4c2c56c203d8d9226d2059badf389244a7b9f22bee2
|
| 3 |
+
size 2401525449
|
checkpoint-25000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32a7c3d6a8844136768df09219aa227a5bf6459182fc8fe953da19e3e1e0e8e1
|
| 3 |
+
size 1200770757
|
checkpoint-25000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec8034f1eca0cc399645d649414d99af5b3835fcd2b75116953f7395d01c69fa
|
| 3 |
+
size 14503
|
checkpoint-25000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0385a8d6f522156056a73e08256fec115925bc81c6a007e8c382eb6bc9ee6ca
|
| 3 |
+
size 623
|
checkpoint-25000/trainer_state.json
ADDED
|
@@ -0,0 +1,846 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.5242392141022614,
|
| 5 |
+
"global_step": 25000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.9951222486433756e-05,
|
| 13 |
+
"loss": 0.0754,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 1.990244497286751e-05,
|
| 19 |
+
"loss": 0.0747,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 1.9853667459301263e-05,
|
| 25 |
+
"loss": 0.0737,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 1.9804889945735017e-05,
|
| 31 |
+
"loss": 0.073,
|
| 32 |
+
"step": 800
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"learning_rate": 1.975611243216877e-05,
|
| 37 |
+
"loss": 0.0723,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.07,
|
| 42 |
+
"learning_rate": 1.9707334918602525e-05,
|
| 43 |
+
"loss": 0.072,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.09,
|
| 48 |
+
"learning_rate": 1.965855740503628e-05,
|
| 49 |
+
"loss": 0.0709,
|
| 50 |
+
"step": 1400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.1,
|
| 54 |
+
"learning_rate": 1.9609779891470033e-05,
|
| 55 |
+
"loss": 0.0703,
|
| 56 |
+
"step": 1600
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.11,
|
| 60 |
+
"learning_rate": 1.9561002377903787e-05,
|
| 61 |
+
"loss": 0.0708,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.12,
|
| 66 |
+
"learning_rate": 1.951222486433754e-05,
|
| 67 |
+
"loss": 0.0711,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.13,
|
| 72 |
+
"learning_rate": 1.9463447350771295e-05,
|
| 73 |
+
"loss": 0.0699,
|
| 74 |
+
"step": 2200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.15,
|
| 78 |
+
"learning_rate": 1.941466983720505e-05,
|
| 79 |
+
"loss": 0.0701,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15,
|
| 84 |
+
"eval_loss": 0.055753033608198166,
|
| 85 |
+
"eval_runtime": 1008.1775,
|
| 86 |
+
"eval_samples_per_second": 82.199,
|
| 87 |
+
"eval_steps_per_second": 13.7,
|
| 88 |
+
"step": 2500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.16,
|
| 92 |
+
"learning_rate": 1.9365892323638806e-05,
|
| 93 |
+
"loss": 0.071,
|
| 94 |
+
"step": 2600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17,
|
| 98 |
+
"learning_rate": 1.931711481007256e-05,
|
| 99 |
+
"loss": 0.0692,
|
| 100 |
+
"step": 2800
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.18,
|
| 104 |
+
"learning_rate": 1.9268337296506314e-05,
|
| 105 |
+
"loss": 0.0687,
|
| 106 |
+
"step": 3000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.2,
|
| 110 |
+
"learning_rate": 1.9219559782940067e-05,
|
| 111 |
+
"loss": 0.0689,
|
| 112 |
+
"step": 3200
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.21,
|
| 116 |
+
"learning_rate": 1.917078226937382e-05,
|
| 117 |
+
"loss": 0.0681,
|
| 118 |
+
"step": 3400
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.22,
|
| 122 |
+
"learning_rate": 1.9122004755807575e-05,
|
| 123 |
+
"loss": 0.0678,
|
| 124 |
+
"step": 3600
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.23,
|
| 128 |
+
"learning_rate": 1.907322724224133e-05,
|
| 129 |
+
"loss": 0.0666,
|
| 130 |
+
"step": 3800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.24,
|
| 134 |
+
"learning_rate": 1.9024449728675083e-05,
|
| 135 |
+
"loss": 0.0676,
|
| 136 |
+
"step": 4000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.26,
|
| 140 |
+
"learning_rate": 1.8975672215108837e-05,
|
| 141 |
+
"loss": 0.0662,
|
| 142 |
+
"step": 4200
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.27,
|
| 146 |
+
"learning_rate": 1.892689470154259e-05,
|
| 147 |
+
"loss": 0.0676,
|
| 148 |
+
"step": 4400
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.28,
|
| 152 |
+
"learning_rate": 1.8878117187976345e-05,
|
| 153 |
+
"loss": 0.0663,
|
| 154 |
+
"step": 4600
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.29,
|
| 158 |
+
"learning_rate": 1.88293396744101e-05,
|
| 159 |
+
"loss": 0.0661,
|
| 160 |
+
"step": 4800
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.3,
|
| 164 |
+
"learning_rate": 1.8780562160843853e-05,
|
| 165 |
+
"loss": 0.0661,
|
| 166 |
+
"step": 5000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.3,
|
| 170 |
+
"eval_loss": 0.05344025790691376,
|
| 171 |
+
"eval_runtime": 1009.8843,
|
| 172 |
+
"eval_samples_per_second": 82.06,
|
| 173 |
+
"eval_steps_per_second": 13.677,
|
| 174 |
+
"step": 5000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.32,
|
| 178 |
+
"learning_rate": 1.8731784647277606e-05,
|
| 179 |
+
"loss": 0.0674,
|
| 180 |
+
"step": 5200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.33,
|
| 184 |
+
"learning_rate": 1.868300713371136e-05,
|
| 185 |
+
"loss": 0.066,
|
| 186 |
+
"step": 5400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.34,
|
| 190 |
+
"learning_rate": 1.8634229620145114e-05,
|
| 191 |
+
"loss": 0.0642,
|
| 192 |
+
"step": 5600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.35,
|
| 196 |
+
"learning_rate": 1.8585452106578868e-05,
|
| 197 |
+
"loss": 0.0655,
|
| 198 |
+
"step": 5800
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.37,
|
| 202 |
+
"learning_rate": 1.8536674593012622e-05,
|
| 203 |
+
"loss": 0.0654,
|
| 204 |
+
"step": 6000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.38,
|
| 208 |
+
"learning_rate": 1.8487897079446376e-05,
|
| 209 |
+
"loss": 0.0641,
|
| 210 |
+
"step": 6200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.39,
|
| 214 |
+
"learning_rate": 1.843911956588013e-05,
|
| 215 |
+
"loss": 0.0636,
|
| 216 |
+
"step": 6400
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.4,
|
| 220 |
+
"learning_rate": 1.8390342052313884e-05,
|
| 221 |
+
"loss": 0.0658,
|
| 222 |
+
"step": 6600
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.41,
|
| 226 |
+
"learning_rate": 1.8341564538747638e-05,
|
| 227 |
+
"loss": 0.0639,
|
| 228 |
+
"step": 6800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.43,
|
| 232 |
+
"learning_rate": 1.8292787025181395e-05,
|
| 233 |
+
"loss": 0.0642,
|
| 234 |
+
"step": 7000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.44,
|
| 238 |
+
"learning_rate": 1.8244009511615145e-05,
|
| 239 |
+
"loss": 0.0648,
|
| 240 |
+
"step": 7200
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.45,
|
| 244 |
+
"learning_rate": 1.8195231998048903e-05,
|
| 245 |
+
"loss": 0.0645,
|
| 246 |
+
"step": 7400
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.46,
|
| 250 |
+
"eval_loss": 0.05153830349445343,
|
| 251 |
+
"eval_runtime": 1007.6883,
|
| 252 |
+
"eval_samples_per_second": 82.239,
|
| 253 |
+
"eval_steps_per_second": 13.707,
|
| 254 |
+
"step": 7500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.46,
|
| 258 |
+
"learning_rate": 1.8146454484482653e-05,
|
| 259 |
+
"loss": 0.0639,
|
| 260 |
+
"step": 7600
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.48,
|
| 264 |
+
"learning_rate": 1.809767697091641e-05,
|
| 265 |
+
"loss": 0.0628,
|
| 266 |
+
"step": 7800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.49,
|
| 270 |
+
"learning_rate": 1.8048899457350164e-05,
|
| 271 |
+
"loss": 0.0647,
|
| 272 |
+
"step": 8000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.5,
|
| 276 |
+
"learning_rate": 1.800012194378392e-05,
|
| 277 |
+
"loss": 0.0629,
|
| 278 |
+
"step": 8200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.51,
|
| 282 |
+
"learning_rate": 1.7951344430217672e-05,
|
| 283 |
+
"loss": 0.0638,
|
| 284 |
+
"step": 8400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.52,
|
| 288 |
+
"learning_rate": 1.7902566916651426e-05,
|
| 289 |
+
"loss": 0.0635,
|
| 290 |
+
"step": 8600
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.54,
|
| 294 |
+
"learning_rate": 1.785378940308518e-05,
|
| 295 |
+
"loss": 0.0628,
|
| 296 |
+
"step": 8800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.55,
|
| 300 |
+
"learning_rate": 1.7805011889518934e-05,
|
| 301 |
+
"loss": 0.063,
|
| 302 |
+
"step": 9000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.56,
|
| 306 |
+
"learning_rate": 1.7756234375952688e-05,
|
| 307 |
+
"loss": 0.0636,
|
| 308 |
+
"step": 9200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.57,
|
| 312 |
+
"learning_rate": 1.7707456862386442e-05,
|
| 313 |
+
"loss": 0.0633,
|
| 314 |
+
"step": 9400
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.59,
|
| 318 |
+
"learning_rate": 1.7658679348820196e-05,
|
| 319 |
+
"loss": 0.0624,
|
| 320 |
+
"step": 9600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.6,
|
| 324 |
+
"learning_rate": 1.760990183525395e-05,
|
| 325 |
+
"loss": 0.0615,
|
| 326 |
+
"step": 9800
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.61,
|
| 330 |
+
"learning_rate": 1.7561124321687703e-05,
|
| 331 |
+
"loss": 0.062,
|
| 332 |
+
"step": 10000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.61,
|
| 336 |
+
"eval_loss": 0.05109347030520439,
|
| 337 |
+
"eval_runtime": 1005.611,
|
| 338 |
+
"eval_samples_per_second": 82.409,
|
| 339 |
+
"eval_steps_per_second": 13.735,
|
| 340 |
+
"step": 10000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.62,
|
| 344 |
+
"learning_rate": 1.7512346808121457e-05,
|
| 345 |
+
"loss": 0.0616,
|
| 346 |
+
"step": 10200
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.63,
|
| 350 |
+
"learning_rate": 1.746356929455521e-05,
|
| 351 |
+
"loss": 0.0613,
|
| 352 |
+
"step": 10400
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.65,
|
| 356 |
+
"learning_rate": 1.7414791780988965e-05,
|
| 357 |
+
"loss": 0.0616,
|
| 358 |
+
"step": 10600
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.66,
|
| 362 |
+
"learning_rate": 1.736601426742272e-05,
|
| 363 |
+
"loss": 0.0623,
|
| 364 |
+
"step": 10800
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.67,
|
| 368 |
+
"learning_rate": 1.7317236753856473e-05,
|
| 369 |
+
"loss": 0.062,
|
| 370 |
+
"step": 11000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.68,
|
| 374 |
+
"learning_rate": 1.7268459240290227e-05,
|
| 375 |
+
"loss": 0.0632,
|
| 376 |
+
"step": 11200
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.7,
|
| 380 |
+
"learning_rate": 1.7219681726723984e-05,
|
| 381 |
+
"loss": 0.0623,
|
| 382 |
+
"step": 11400
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.71,
|
| 386 |
+
"learning_rate": 1.7170904213157735e-05,
|
| 387 |
+
"loss": 0.0608,
|
| 388 |
+
"step": 11600
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.72,
|
| 392 |
+
"learning_rate": 1.7122126699591492e-05,
|
| 393 |
+
"loss": 0.061,
|
| 394 |
+
"step": 11800
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.73,
|
| 398 |
+
"learning_rate": 1.7073349186025242e-05,
|
| 399 |
+
"loss": 0.061,
|
| 400 |
+
"step": 12000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.74,
|
| 404 |
+
"learning_rate": 1.7024571672459e-05,
|
| 405 |
+
"loss": 0.0605,
|
| 406 |
+
"step": 12200
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.76,
|
| 410 |
+
"learning_rate": 1.697579415889275e-05,
|
| 411 |
+
"loss": 0.0607,
|
| 412 |
+
"step": 12400
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.76,
|
| 416 |
+
"eval_loss": 0.04968786612153053,
|
| 417 |
+
"eval_runtime": 1006.7134,
|
| 418 |
+
"eval_samples_per_second": 82.318,
|
| 419 |
+
"eval_steps_per_second": 13.72,
|
| 420 |
+
"step": 12500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.77,
|
| 424 |
+
"learning_rate": 1.6927016645326508e-05,
|
| 425 |
+
"loss": 0.0616,
|
| 426 |
+
"step": 12600
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.78,
|
| 430 |
+
"learning_rate": 1.6878239131760258e-05,
|
| 431 |
+
"loss": 0.0596,
|
| 432 |
+
"step": 12800
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.79,
|
| 436 |
+
"learning_rate": 1.6829461618194015e-05,
|
| 437 |
+
"loss": 0.0615,
|
| 438 |
+
"step": 13000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.8,
|
| 442 |
+
"learning_rate": 1.6780684104627766e-05,
|
| 443 |
+
"loss": 0.0599,
|
| 444 |
+
"step": 13200
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.82,
|
| 448 |
+
"learning_rate": 1.6731906591061523e-05,
|
| 449 |
+
"loss": 0.0598,
|
| 450 |
+
"step": 13400
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.83,
|
| 454 |
+
"learning_rate": 1.6683129077495277e-05,
|
| 455 |
+
"loss": 0.0606,
|
| 456 |
+
"step": 13600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.84,
|
| 460 |
+
"learning_rate": 1.663435156392903e-05,
|
| 461 |
+
"loss": 0.0596,
|
| 462 |
+
"step": 13800
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.85,
|
| 466 |
+
"learning_rate": 1.6585574050362785e-05,
|
| 467 |
+
"loss": 0.0585,
|
| 468 |
+
"step": 14000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.87,
|
| 472 |
+
"learning_rate": 1.653679653679654e-05,
|
| 473 |
+
"loss": 0.0597,
|
| 474 |
+
"step": 14200
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.88,
|
| 478 |
+
"learning_rate": 1.6488019023230293e-05,
|
| 479 |
+
"loss": 0.0606,
|
| 480 |
+
"step": 14400
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.89,
|
| 484 |
+
"learning_rate": 1.6439241509664047e-05,
|
| 485 |
+
"loss": 0.0591,
|
| 486 |
+
"step": 14600
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9,
|
| 490 |
+
"learning_rate": 1.63904639960978e-05,
|
| 491 |
+
"loss": 0.06,
|
| 492 |
+
"step": 14800
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.91,
|
| 496 |
+
"learning_rate": 1.6341686482531554e-05,
|
| 497 |
+
"loss": 0.0586,
|
| 498 |
+
"step": 15000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.91,
|
| 502 |
+
"eval_loss": 0.04891153797507286,
|
| 503 |
+
"eval_runtime": 1009.9343,
|
| 504 |
+
"eval_samples_per_second": 82.056,
|
| 505 |
+
"eval_steps_per_second": 13.676,
|
| 506 |
+
"step": 15000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.93,
|
| 510 |
+
"learning_rate": 1.6292908968965308e-05,
|
| 511 |
+
"loss": 0.06,
|
| 512 |
+
"step": 15200
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.94,
|
| 516 |
+
"learning_rate": 1.6244131455399062e-05,
|
| 517 |
+
"loss": 0.0587,
|
| 518 |
+
"step": 15400
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.95,
|
| 522 |
+
"learning_rate": 1.6195353941832816e-05,
|
| 523 |
+
"loss": 0.0584,
|
| 524 |
+
"step": 15600
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.96,
|
| 528 |
+
"learning_rate": 1.614657642826657e-05,
|
| 529 |
+
"loss": 0.0602,
|
| 530 |
+
"step": 15800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.98,
|
| 534 |
+
"learning_rate": 1.6097798914700324e-05,
|
| 535 |
+
"loss": 0.0587,
|
| 536 |
+
"step": 16000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.99,
|
| 540 |
+
"learning_rate": 1.604902140113408e-05,
|
| 541 |
+
"loss": 0.0578,
|
| 542 |
+
"step": 16200
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.0,
|
| 546 |
+
"learning_rate": 1.600024388756783e-05,
|
| 547 |
+
"loss": 0.0578,
|
| 548 |
+
"step": 16400
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.01,
|
| 552 |
+
"learning_rate": 1.595146637400159e-05,
|
| 553 |
+
"loss": 0.0598,
|
| 554 |
+
"step": 16600
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.02,
|
| 558 |
+
"learning_rate": 1.590268886043534e-05,
|
| 559 |
+
"loss": 0.0583,
|
| 560 |
+
"step": 16800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.04,
|
| 564 |
+
"learning_rate": 1.5853911346869097e-05,
|
| 565 |
+
"loss": 0.0577,
|
| 566 |
+
"step": 17000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.05,
|
| 570 |
+
"learning_rate": 1.5805133833302847e-05,
|
| 571 |
+
"loss": 0.0571,
|
| 572 |
+
"step": 17200
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.06,
|
| 576 |
+
"learning_rate": 1.5756356319736604e-05,
|
| 577 |
+
"loss": 0.0583,
|
| 578 |
+
"step": 17400
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.07,
|
| 582 |
+
"eval_loss": 0.048093125224113464,
|
| 583 |
+
"eval_runtime": 1004.9925,
|
| 584 |
+
"eval_samples_per_second": 82.459,
|
| 585 |
+
"eval_steps_per_second": 13.743,
|
| 586 |
+
"step": 17500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.07,
|
| 590 |
+
"learning_rate": 1.5707578806170355e-05,
|
| 591 |
+
"loss": 0.0588,
|
| 592 |
+
"step": 17600
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.09,
|
| 596 |
+
"learning_rate": 1.5658801292604112e-05,
|
| 597 |
+
"loss": 0.0578,
|
| 598 |
+
"step": 17800
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.1,
|
| 602 |
+
"learning_rate": 1.5610023779037863e-05,
|
| 603 |
+
"loss": 0.0584,
|
| 604 |
+
"step": 18000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.11,
|
| 608 |
+
"learning_rate": 1.556124626547162e-05,
|
| 609 |
+
"loss": 0.0569,
|
| 610 |
+
"step": 18200
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.12,
|
| 614 |
+
"learning_rate": 1.551246875190537e-05,
|
| 615 |
+
"loss": 0.0575,
|
| 616 |
+
"step": 18400
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.13,
|
| 620 |
+
"learning_rate": 1.5463691238339128e-05,
|
| 621 |
+
"loss": 0.058,
|
| 622 |
+
"step": 18600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.15,
|
| 626 |
+
"learning_rate": 1.5414913724772882e-05,
|
| 627 |
+
"loss": 0.0562,
|
| 628 |
+
"step": 18800
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.16,
|
| 632 |
+
"learning_rate": 1.5366136211206636e-05,
|
| 633 |
+
"loss": 0.0586,
|
| 634 |
+
"step": 19000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.17,
|
| 638 |
+
"learning_rate": 1.531735869764039e-05,
|
| 639 |
+
"loss": 0.0576,
|
| 640 |
+
"step": 19200
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.18,
|
| 644 |
+
"learning_rate": 1.5268581184074143e-05,
|
| 645 |
+
"loss": 0.0578,
|
| 646 |
+
"step": 19400
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.2,
|
| 650 |
+
"learning_rate": 1.5219803670507897e-05,
|
| 651 |
+
"loss": 0.0571,
|
| 652 |
+
"step": 19600
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.21,
|
| 656 |
+
"learning_rate": 1.5171026156941651e-05,
|
| 657 |
+
"loss": 0.0564,
|
| 658 |
+
"step": 19800
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.22,
|
| 662 |
+
"learning_rate": 1.5122248643375405e-05,
|
| 663 |
+
"loss": 0.0578,
|
| 664 |
+
"step": 20000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.22,
|
| 668 |
+
"eval_loss": 0.047511521726846695,
|
| 669 |
+
"eval_runtime": 1012.2966,
|
| 670 |
+
"eval_samples_per_second": 81.864,
|
| 671 |
+
"eval_steps_per_second": 13.644,
|
| 672 |
+
"step": 20000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.23,
|
| 676 |
+
"learning_rate": 1.5073471129809159e-05,
|
| 677 |
+
"loss": 0.0573,
|
| 678 |
+
"step": 20200
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.24,
|
| 682 |
+
"learning_rate": 1.5024693616242913e-05,
|
| 683 |
+
"loss": 0.0577,
|
| 684 |
+
"step": 20400
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.26,
|
| 688 |
+
"learning_rate": 1.4975916102676667e-05,
|
| 689 |
+
"loss": 0.0571,
|
| 690 |
+
"step": 20600
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.27,
|
| 694 |
+
"learning_rate": 1.492713858911042e-05,
|
| 695 |
+
"loss": 0.0571,
|
| 696 |
+
"step": 20800
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.28,
|
| 700 |
+
"learning_rate": 1.4878361075544175e-05,
|
| 701 |
+
"loss": 0.0573,
|
| 702 |
+
"step": 21000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.29,
|
| 706 |
+
"learning_rate": 1.4829583561977929e-05,
|
| 707 |
+
"loss": 0.0571,
|
| 708 |
+
"step": 21200
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 1.3,
|
| 712 |
+
"learning_rate": 1.4780806048411684e-05,
|
| 713 |
+
"loss": 0.0574,
|
| 714 |
+
"step": 21400
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.32,
|
| 718 |
+
"learning_rate": 1.4732028534845438e-05,
|
| 719 |
+
"loss": 0.0565,
|
| 720 |
+
"step": 21600
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.33,
|
| 724 |
+
"learning_rate": 1.4683251021279192e-05,
|
| 725 |
+
"loss": 0.0564,
|
| 726 |
+
"step": 21800
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.34,
|
| 730 |
+
"learning_rate": 1.4634473507712946e-05,
|
| 731 |
+
"loss": 0.0563,
|
| 732 |
+
"step": 22000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.35,
|
| 736 |
+
"learning_rate": 1.45856959941467e-05,
|
| 737 |
+
"loss": 0.0564,
|
| 738 |
+
"step": 22200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.37,
|
| 742 |
+
"learning_rate": 1.4536918480580454e-05,
|
| 743 |
+
"loss": 0.0557,
|
| 744 |
+
"step": 22400
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.37,
|
| 748 |
+
"eval_loss": 0.04695958271622658,
|
| 749 |
+
"eval_runtime": 1007.3223,
|
| 750 |
+
"eval_samples_per_second": 82.269,
|
| 751 |
+
"eval_steps_per_second": 13.712,
|
| 752 |
+
"step": 22500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.38,
|
| 756 |
+
"learning_rate": 1.4488140967014208e-05,
|
| 757 |
+
"loss": 0.0563,
|
| 758 |
+
"step": 22600
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.39,
|
| 762 |
+
"learning_rate": 1.4439363453447961e-05,
|
| 763 |
+
"loss": 0.0555,
|
| 764 |
+
"step": 22800
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.4,
|
| 768 |
+
"learning_rate": 1.4390585939881715e-05,
|
| 769 |
+
"loss": 0.0567,
|
| 770 |
+
"step": 23000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.41,
|
| 774 |
+
"learning_rate": 1.434180842631547e-05,
|
| 775 |
+
"loss": 0.0563,
|
| 776 |
+
"step": 23200
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 1.43,
|
| 780 |
+
"learning_rate": 1.4293030912749223e-05,
|
| 781 |
+
"loss": 0.0568,
|
| 782 |
+
"step": 23400
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.44,
|
| 786 |
+
"learning_rate": 1.4244253399182977e-05,
|
| 787 |
+
"loss": 0.0552,
|
| 788 |
+
"step": 23600
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.45,
|
| 792 |
+
"learning_rate": 1.4195475885616733e-05,
|
| 793 |
+
"loss": 0.0564,
|
| 794 |
+
"step": 23800
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.46,
|
| 798 |
+
"learning_rate": 1.4146698372050487e-05,
|
| 799 |
+
"loss": 0.0558,
|
| 800 |
+
"step": 24000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.48,
|
| 804 |
+
"learning_rate": 1.409792085848424e-05,
|
| 805 |
+
"loss": 0.0553,
|
| 806 |
+
"step": 24200
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 1.49,
|
| 810 |
+
"learning_rate": 1.4049143344917994e-05,
|
| 811 |
+
"loss": 0.0545,
|
| 812 |
+
"step": 24400
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.5,
|
| 816 |
+
"learning_rate": 1.4000365831351748e-05,
|
| 817 |
+
"loss": 0.0551,
|
| 818 |
+
"step": 24600
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.51,
|
| 822 |
+
"learning_rate": 1.3951588317785502e-05,
|
| 823 |
+
"loss": 0.0556,
|
| 824 |
+
"step": 24800
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.52,
|
| 828 |
+
"learning_rate": 1.3902810804219256e-05,
|
| 829 |
+
"loss": 0.0543,
|
| 830 |
+
"step": 25000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 1.52,
|
| 834 |
+
"eval_loss": 0.04659077152609825,
|
| 835 |
+
"eval_runtime": 1008.4315,
|
| 836 |
+
"eval_samples_per_second": 82.178,
|
| 837 |
+
"eval_steps_per_second": 13.697,
|
| 838 |
+
"step": 25000
|
| 839 |
+
}
|
| 840 |
+
],
|
| 841 |
+
"max_steps": 82005,
|
| 842 |
+
"num_train_epochs": 5,
|
| 843 |
+
"total_flos": 1.2689982006126182e+18,
|
| 844 |
+
"trial_name": null,
|
| 845 |
+
"trial_params": null
|
| 846 |
+
}
|
checkpoint-25000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69cea6267551e6c3db2312cb16b8e111ea7cc82c9a729b741a0cc0164750a77c
|
| 3 |
+
size 3695
|