Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- GoNotoCurrent.ttf +3 -0
- config.json +57 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- text_renderer_config.json +11 -0
- trainer_state.json +756 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
GoNotoCurrent.ttf filter=lfs diff=lfs merge=lfs -text
|
GoNotoCurrent.ttf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
|
| 3 |
+
size 15645492
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"PIXBAForPreTraining"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bias": false,
|
| 7 |
+
"cache_dir": null,
|
| 8 |
+
"conv_bias": true,
|
| 9 |
+
"d_conv": 4,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"d_state": 16,
|
| 12 |
+
"decoder_hidden_size": 512,
|
| 13 |
+
"decoder_intermediate_size": 2048,
|
| 14 |
+
"decoder_num_attention_heads": 16,
|
| 15 |
+
"decoder_num_hidden_layers": 8,
|
| 16 |
+
"device": null,
|
| 17 |
+
"dt_init": "random",
|
| 18 |
+
"dt_init_floor": 0.0001,
|
| 19 |
+
"dt_max": 0.1,
|
| 20 |
+
"dt_min": 0.001,
|
| 21 |
+
"dt_rank": "auto",
|
| 22 |
+
"dt_scale": 1.0,
|
| 23 |
+
"dtype": null,
|
| 24 |
+
"expand": 2,
|
| 25 |
+
"fused_add_norm": true,
|
| 26 |
+
"hidden_act": "gelu",
|
| 27 |
+
"hidden_dropout_prob": 0.1,
|
| 28 |
+
"hidden_size": 768,
|
| 29 |
+
"image_size": [
|
| 30 |
+
16,
|
| 31 |
+
8464
|
| 32 |
+
],
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"layer_norm_eps": 1e-12,
|
| 36 |
+
"mask_ratio": 0.25,
|
| 37 |
+
"model_type": "pixel",
|
| 38 |
+
"norm_pix_loss": true,
|
| 39 |
+
"num_attention_heads": 12,
|
| 40 |
+
"num_channels": 3,
|
| 41 |
+
"num_decoder_layers": 2,
|
| 42 |
+
"num_encoder_layers": 4,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"num_patches": 529,
|
| 45 |
+
"pad_vocab_size_multiple": 8,
|
| 46 |
+
"patch_size": 16,
|
| 47 |
+
"qkv_bias": true,
|
| 48 |
+
"residual_in_fp32": true,
|
| 49 |
+
"revision": "main",
|
| 50 |
+
"rms_norm": true,
|
| 51 |
+
"ssm_cfg": {},
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.17.0",
|
| 54 |
+
"use_auth_token": "redacted hf token",
|
| 55 |
+
"use_fast_path": true,
|
| 56 |
+
"vocab_size": 50277
|
| 57 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76bbb28776a1b69165e95d589dcd3485cf2feccd73dcd426bb863ee1f015c3d4
|
| 3 |
+
size 190607546
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb8b6e57dc3f67a23986123e255ee6e5140b44dea62499f4f872bad142a329e
|
| 3 |
+
size 98566808
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47b9ab4ef52f698ad7dd4dd0b4b7a2051ff44012e3e4cc8a8f43481e7e235b0e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5243151c67e530455e992605b2451b5ddabc9a1e01446e6f8e5220dafd1ecb34
|
| 3 |
+
size 1064
|
text_renderer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"background_color": "white",
|
| 3 |
+
"dpi": 120,
|
| 4 |
+
"font_color": "black",
|
| 5 |
+
"font_file": "GoNotoCurrent.ttf",
|
| 6 |
+
"font_size": 8,
|
| 7 |
+
"max_seq_length": 529,
|
| 8 |
+
"pad_size": 3,
|
| 9 |
+
"pixels_per_patch": 16,
|
| 10 |
+
"text_renderer_type": "PyGameTextRenderer"
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,756 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.1255810812331866,
|
| 5 |
+
"global_step": 100000,
|
| 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": 2.1425510641336953e-05,
|
| 13 |
+
"loss": 0.8766,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.2851021282673906e-05,
|
| 19 |
+
"loss": 0.4593,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 6.427653192401085e-05,
|
| 25 |
+
"loss": 0.4128,
|
| 26 |
+
"step": 3000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 8.570204256534781e-05,
|
| 31 |
+
"loss": 0.3927,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"learning_rate": 0.00010712755320668476,
|
| 37 |
+
"loss": 0.3799,
|
| 38 |
+
"step": 5000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06,
|
| 42 |
+
"eval_runtime": 104.0589,
|
| 43 |
+
"eval_samples_per_second": 1100.002,
|
| 44 |
+
"eval_steps_per_second": 137.509,
|
| 45 |
+
"step": 5000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07,
|
| 49 |
+
"learning_rate": 0.0001285530638480217,
|
| 50 |
+
"loss": 0.3716,
|
| 51 |
+
"step": 6000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"learning_rate": 0.00014997857448935864,
|
| 56 |
+
"loss": 0.3637,
|
| 57 |
+
"step": 7000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09,
|
| 61 |
+
"learning_rate": 0.00014996014333179132,
|
| 62 |
+
"loss": 0.3579,
|
| 63 |
+
"step": 8000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.1,
|
| 67 |
+
"learning_rate": 0.00014984045919431678,
|
| 68 |
+
"loss": 0.3522,
|
| 69 |
+
"step": 9000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.11,
|
| 73 |
+
"learning_rate": 0.0001496410841123446,
|
| 74 |
+
"loss": 0.3463,
|
| 75 |
+
"step": 10000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.11,
|
| 79 |
+
"eval_runtime": 104.0864,
|
| 80 |
+
"eval_samples_per_second": 1099.711,
|
| 81 |
+
"eval_steps_per_second": 137.472,
|
| 82 |
+
"step": 10000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.12,
|
| 86 |
+
"learning_rate": 0.00014936224558135207,
|
| 87 |
+
"loss": 0.3425,
|
| 88 |
+
"step": 11000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.14,
|
| 92 |
+
"learning_rate": 0.0001490042617680029,
|
| 93 |
+
"loss": 0.3388,
|
| 94 |
+
"step": 12000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"learning_rate": 0.00014856754114710562,
|
| 99 |
+
"loss": 0.3349,
|
| 100 |
+
"step": 13000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.16,
|
| 104 |
+
"learning_rate": 0.00014805258203552652,
|
| 105 |
+
"loss": 0.3325,
|
| 106 |
+
"step": 14000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.17,
|
| 110 |
+
"learning_rate": 0.0001474599720235886,
|
| 111 |
+
"loss": 0.3305,
|
| 112 |
+
"step": 15000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.17,
|
| 116 |
+
"eval_runtime": 103.2729,
|
| 117 |
+
"eval_samples_per_second": 1108.374,
|
| 118 |
+
"eval_steps_per_second": 138.555,
|
| 119 |
+
"step": 15000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.18,
|
| 123 |
+
"learning_rate": 0.0001467903873046061,
|
| 124 |
+
"loss": 0.3271,
|
| 125 |
+
"step": 16000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.19,
|
| 129 |
+
"learning_rate": 0.00014604459190331901,
|
| 130 |
+
"loss": 0.324,
|
| 131 |
+
"step": 17000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.2,
|
| 135 |
+
"learning_rate": 0.00014522343680410828,
|
| 136 |
+
"loss": 0.3229,
|
| 137 |
+
"step": 18000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.21,
|
| 141 |
+
"learning_rate": 0.00014432785897998624,
|
| 142 |
+
"loss": 0.3206,
|
| 143 |
+
"step": 19000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.23,
|
| 147 |
+
"learning_rate": 0.00014335888032347046,
|
| 148 |
+
"loss": 0.3189,
|
| 149 |
+
"step": 20000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.23,
|
| 153 |
+
"eval_runtime": 104.205,
|
| 154 |
+
"eval_samples_per_second": 1098.46,
|
| 155 |
+
"eval_steps_per_second": 137.316,
|
| 156 |
+
"step": 20000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24,
|
| 160 |
+
"learning_rate": 0.00014231760648056077,
|
| 161 |
+
"loss": 0.3168,
|
| 162 |
+
"step": 21000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.25,
|
| 166 |
+
"learning_rate": 0.00014120522558915008,
|
| 167 |
+
"loss": 0.3157,
|
| 168 |
+
"step": 22000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.26,
|
| 172 |
+
"learning_rate": 0.00014002300692330812,
|
| 173 |
+
"loss": 0.3141,
|
| 174 |
+
"step": 23000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.27,
|
| 178 |
+
"learning_rate": 0.00013877229944498577,
|
| 179 |
+
"loss": 0.3124,
|
| 180 |
+
"step": 24000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.28,
|
| 184 |
+
"learning_rate": 0.00013745453026479178,
|
| 185 |
+
"loss": 0.3114,
|
| 186 |
+
"step": 25000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.28,
|
| 190 |
+
"eval_runtime": 104.294,
|
| 191 |
+
"eval_samples_per_second": 1097.522,
|
| 192 |
+
"eval_steps_per_second": 137.199,
|
| 193 |
+
"step": 25000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.29,
|
| 197 |
+
"learning_rate": 0.00013607120301359875,
|
| 198 |
+
"loss": 0.3102,
|
| 199 |
+
"step": 26000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3,
|
| 203 |
+
"learning_rate": 0.00013462389612683607,
|
| 204 |
+
"loss": 0.309,
|
| 205 |
+
"step": 27000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.32,
|
| 209 |
+
"learning_rate": 0.00013311426104342775,
|
| 210 |
+
"loss": 0.3079,
|
| 211 |
+
"step": 28000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.33,
|
| 215 |
+
"learning_rate": 0.0001315440203214301,
|
| 216 |
+
"loss": 0.3066,
|
| 217 |
+
"step": 29000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.34,
|
| 221 |
+
"learning_rate": 0.00012991496567251953,
|
| 222 |
+
"loss": 0.3065,
|
| 223 |
+
"step": 30000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.34,
|
| 227 |
+
"eval_runtime": 103.1778,
|
| 228 |
+
"eval_samples_per_second": 1109.395,
|
| 229 |
+
"eval_steps_per_second": 138.683,
|
| 230 |
+
"step": 30000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.35,
|
| 234 |
+
"learning_rate": 0.00012822895591757308,
|
| 235 |
+
"loss": 0.3058,
|
| 236 |
+
"step": 31000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.36,
|
| 240 |
+
"learning_rate": 0.0001264879148656744,
|
| 241 |
+
"loss": 0.3046,
|
| 242 |
+
"step": 32000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.37,
|
| 246 |
+
"learning_rate": 0.00012469382911896545,
|
| 247 |
+
"loss": 0.3041,
|
| 248 |
+
"step": 33000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.38,
|
| 252 |
+
"learning_rate": 0.00012284874580584883,
|
| 253 |
+
"loss": 0.3039,
|
| 254 |
+
"step": 34000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.39,
|
| 258 |
+
"learning_rate": 0.00012095477024512678,
|
| 259 |
+
"loss": 0.3029,
|
| 260 |
+
"step": 35000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.39,
|
| 264 |
+
"eval_runtime": 104.2139,
|
| 265 |
+
"eval_samples_per_second": 1098.366,
|
| 266 |
+
"eval_steps_per_second": 137.304,
|
| 267 |
+
"step": 35000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.41,
|
| 271 |
+
"learning_rate": 0.00011901406354374264,
|
| 272 |
+
"loss": 0.3022,
|
| 273 |
+
"step": 36000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.42,
|
| 277 |
+
"learning_rate": 0.00011702884013086549,
|
| 278 |
+
"loss": 0.301,
|
| 279 |
+
"step": 37000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.43,
|
| 283 |
+
"learning_rate": 0.00011500136523113215,
|
| 284 |
+
"loss": 0.3009,
|
| 285 |
+
"step": 38000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.44,
|
| 289 |
+
"learning_rate": 0.00011293395227992909,
|
| 290 |
+
"loss": 0.3007,
|
| 291 |
+
"step": 39000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.45,
|
| 295 |
+
"learning_rate": 0.00011082896028366384,
|
| 296 |
+
"loss": 0.2997,
|
| 297 |
+
"step": 40000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.45,
|
| 301 |
+
"eval_runtime": 103.2048,
|
| 302 |
+
"eval_samples_per_second": 1109.105,
|
| 303 |
+
"eval_steps_per_second": 138.647,
|
| 304 |
+
"step": 40000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.46,
|
| 308 |
+
"learning_rate": 0.00010868879112803816,
|
| 309 |
+
"loss": 0.2996,
|
| 310 |
+
"step": 41000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.47,
|
| 314 |
+
"learning_rate": 0.00010651588683739388,
|
| 315 |
+
"loss": 0.2983,
|
| 316 |
+
"step": 42000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.48,
|
| 320 |
+
"learning_rate": 0.00010431272678825886,
|
| 321 |
+
"loss": 0.2986,
|
| 322 |
+
"step": 43000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.5,
|
| 326 |
+
"learning_rate": 0.00010208182488027273,
|
| 327 |
+
"loss": 0.298,
|
| 328 |
+
"step": 44000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.51,
|
| 332 |
+
"learning_rate": 9.982572666771984e-05,
|
| 333 |
+
"loss": 0.2962,
|
| 334 |
+
"step": 45000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.51,
|
| 338 |
+
"eval_runtime": 103.2517,
|
| 339 |
+
"eval_samples_per_second": 1108.601,
|
| 340 |
+
"eval_steps_per_second": 138.584,
|
| 341 |
+
"step": 45000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.52,
|
| 345 |
+
"learning_rate": 9.754700645494349e-05,
|
| 346 |
+
"loss": 0.296,
|
| 347 |
+
"step": 46000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.53,
|
| 351 |
+
"learning_rate": 9.524826435895459e-05,
|
| 352 |
+
"loss": 0.2961,
|
| 353 |
+
"step": 47000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.54,
|
| 357 |
+
"learning_rate": 9.293212334258727e-05,
|
| 358 |
+
"loss": 0.2954,
|
| 359 |
+
"step": 48000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.55,
|
| 363 |
+
"learning_rate": 9.060122622158633e-05,
|
| 364 |
+
"loss": 0.2948,
|
| 365 |
+
"step": 49000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.56,
|
| 369 |
+
"learning_rate": 8.825823264904176e-05,
|
| 370 |
+
"loss": 0.2946,
|
| 371 |
+
"step": 50000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.56,
|
| 375 |
+
"eval_runtime": 103.4614,
|
| 376 |
+
"eval_samples_per_second": 1106.355,
|
| 377 |
+
"eval_steps_per_second": 138.303,
|
| 378 |
+
"step": 50000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.57,
|
| 382 |
+
"learning_rate": 8.590581608061091e-05,
|
| 383 |
+
"loss": 0.2942,
|
| 384 |
+
"step": 51000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.59,
|
| 388 |
+
"learning_rate": 8.354666072399165e-05,
|
| 389 |
+
"loss": 0.2938,
|
| 390 |
+
"step": 52000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.6,
|
| 394 |
+
"learning_rate": 8.118345847612668e-05,
|
| 395 |
+
"loss": 0.2935,
|
| 396 |
+
"step": 53000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.61,
|
| 400 |
+
"learning_rate": 7.881890585163443e-05,
|
| 401 |
+
"loss": 0.2929,
|
| 402 |
+
"step": 54000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.62,
|
| 406 |
+
"learning_rate": 7.645570090597059e-05,
|
| 407 |
+
"loss": 0.292,
|
| 408 |
+
"step": 55000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.62,
|
| 412 |
+
"eval_runtime": 103.3222,
|
| 413 |
+
"eval_samples_per_second": 1107.845,
|
| 414 |
+
"eval_steps_per_second": 138.489,
|
| 415 |
+
"step": 55000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.63,
|
| 419 |
+
"learning_rate": 7.409654015683188e-05,
|
| 420 |
+
"loss": 0.2922,
|
| 421 |
+
"step": 56000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.64,
|
| 425 |
+
"learning_rate": 7.174411550731408e-05,
|
| 426 |
+
"loss": 0.2919,
|
| 427 |
+
"step": 57000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.65,
|
| 431 |
+
"learning_rate": 6.940111117433594e-05,
|
| 432 |
+
"loss": 0.2914,
|
| 433 |
+
"step": 58000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.66,
|
| 437 |
+
"learning_rate": 6.7070200625833e-05,
|
| 438 |
+
"loss": 0.291,
|
| 439 |
+
"step": 59000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.68,
|
| 443 |
+
"learning_rate": 6.475404353021648e-05,
|
| 444 |
+
"loss": 0.2911,
|
| 445 |
+
"step": 60000
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.68,
|
| 449 |
+
"eval_runtime": 104.558,
|
| 450 |
+
"eval_samples_per_second": 1094.752,
|
| 451 |
+
"eval_steps_per_second": 136.852,
|
| 452 |
+
"step": 60000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.69,
|
| 456 |
+
"learning_rate": 6.245528272157836e-05,
|
| 457 |
+
"loss": 0.2903,
|
| 458 |
+
"step": 61000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7,
|
| 462 |
+
"learning_rate": 6.0176541184104665e-05,
|
| 463 |
+
"loss": 0.2897,
|
| 464 |
+
"step": 62000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.71,
|
| 468 |
+
"learning_rate": 5.792041905913877e-05,
|
| 469 |
+
"loss": 0.2895,
|
| 470 |
+
"step": 63000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.72,
|
| 474 |
+
"learning_rate": 5.568949067830892e-05,
|
| 475 |
+
"loss": 0.289,
|
| 476 |
+
"step": 64000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.73,
|
| 480 |
+
"learning_rate": 5.3486301626106276e-05,
|
| 481 |
+
"loss": 0.2894,
|
| 482 |
+
"step": 65000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.73,
|
| 486 |
+
"eval_runtime": 106.3469,
|
| 487 |
+
"eval_samples_per_second": 1076.336,
|
| 488 |
+
"eval_steps_per_second": 134.55,
|
| 489 |
+
"step": 65000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.74,
|
| 493 |
+
"learning_rate": 5.131336583526405e-05,
|
| 494 |
+
"loss": 0.288,
|
| 495 |
+
"step": 66000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.75,
|
| 499 |
+
"learning_rate": 4.917316271825325e-05,
|
| 500 |
+
"loss": 0.2879,
|
| 501 |
+
"step": 67000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.77,
|
| 505 |
+
"learning_rate": 4.706813433816711e-05,
|
| 506 |
+
"loss": 0.2878,
|
| 507 |
+
"step": 68000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.78,
|
| 511 |
+
"learning_rate": 4.500068262222285e-05,
|
| 512 |
+
"loss": 0.287,
|
| 513 |
+
"step": 69000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.79,
|
| 517 |
+
"learning_rate": 4.297316662106028e-05,
|
| 518 |
+
"loss": 0.2874,
|
| 519 |
+
"step": 70000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.79,
|
| 523 |
+
"eval_runtime": 133.9365,
|
| 524 |
+
"eval_samples_per_second": 854.621,
|
| 525 |
+
"eval_steps_per_second": 106.834,
|
| 526 |
+
"step": 70000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.8,
|
| 530 |
+
"learning_rate": 4.098789981696429e-05,
|
| 531 |
+
"loss": 0.2867,
|
| 532 |
+
"step": 71000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.81,
|
| 536 |
+
"learning_rate": 3.904714748408295e-05,
|
| 537 |
+
"loss": 0.2868,
|
| 538 |
+
"step": 72000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.82,
|
| 542 |
+
"learning_rate": 3.715312410365281e-05,
|
| 543 |
+
"loss": 0.2863,
|
| 544 |
+
"step": 73000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.83,
|
| 548 |
+
"learning_rate": 3.530799083718159e-05,
|
| 549 |
+
"loss": 0.2863,
|
| 550 |
+
"step": 74000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.84,
|
| 554 |
+
"learning_rate": 3.351385306047039e-05,
|
| 555 |
+
"loss": 0.286,
|
| 556 |
+
"step": 75000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.84,
|
| 560 |
+
"eval_runtime": 104.105,
|
| 561 |
+
"eval_samples_per_second": 1099.515,
|
| 562 |
+
"eval_steps_per_second": 137.448,
|
| 563 |
+
"step": 75000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.86,
|
| 567 |
+
"learning_rate": 3.177275796129024e-05,
|
| 568 |
+
"loss": 0.2852,
|
| 569 |
+
"step": 76000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.87,
|
| 573 |
+
"learning_rate": 3.008669220345346e-05,
|
| 574 |
+
"loss": 0.2859,
|
| 575 |
+
"step": 77000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.88,
|
| 579 |
+
"learning_rate": 2.8457579659945296e-05,
|
| 580 |
+
"loss": 0.285,
|
| 581 |
+
"step": 78000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.89,
|
| 585 |
+
"learning_rate": 2.6887279217703024e-05,
|
| 586 |
+
"loss": 0.2851,
|
| 587 |
+
"step": 79000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.9,
|
| 591 |
+
"learning_rate": 2.5377582656546377e-05,
|
| 592 |
+
"loss": 0.2845,
|
| 593 |
+
"step": 80000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.9,
|
| 597 |
+
"eval_runtime": 104.5533,
|
| 598 |
+
"eval_samples_per_second": 1094.801,
|
| 599 |
+
"eval_steps_per_second": 136.858,
|
| 600 |
+
"step": 80000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.91,
|
| 604 |
+
"learning_rate": 2.3930212604680446e-05,
|
| 605 |
+
"loss": 0.2844,
|
| 606 |
+
"step": 81000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.92,
|
| 610 |
+
"learning_rate": 2.254682057310328e-05,
|
| 611 |
+
"loss": 0.2847,
|
| 612 |
+
"step": 82000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.93,
|
| 616 |
+
"learning_rate": 2.122898507116151e-05,
|
| 617 |
+
"loss": 0.2841,
|
| 618 |
+
"step": 83000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.95,
|
| 622 |
+
"learning_rate": 1.9978209805403584e-05,
|
| 623 |
+
"loss": 0.2845,
|
| 624 |
+
"step": 84000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.96,
|
| 628 |
+
"learning_rate": 1.8795921963786676e-05,
|
| 629 |
+
"loss": 0.2832,
|
| 630 |
+
"step": 85000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.96,
|
| 634 |
+
"eval_runtime": 103.5197,
|
| 635 |
+
"eval_samples_per_second": 1105.731,
|
| 636 |
+
"eval_steps_per_second": 138.225,
|
| 637 |
+
"step": 85000
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.97,
|
| 641 |
+
"learning_rate": 1.768347058719415e-05,
|
| 642 |
+
"loss": 0.2834,
|
| 643 |
+
"step": 86000
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.98,
|
| 647 |
+
"learning_rate": 1.6642125030122378e-05,
|
| 648 |
+
"loss": 0.2836,
|
| 649 |
+
"step": 87000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.99,
|
| 653 |
+
"learning_rate": 1.5673073512293164e-05,
|
| 654 |
+
"loss": 0.2834,
|
| 655 |
+
"step": 88000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.0,
|
| 659 |
+
"learning_rate": 1.4777421762844163e-05,
|
| 660 |
+
"loss": 0.2832,
|
| 661 |
+
"step": 89000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.01,
|
| 665 |
+
"learning_rate": 1.395619175864496e-05,
|
| 666 |
+
"loss": 0.2824,
|
| 667 |
+
"step": 90000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.01,
|
| 671 |
+
"eval_runtime": 102.1628,
|
| 672 |
+
"eval_samples_per_second": 1120.417,
|
| 673 |
+
"eval_steps_per_second": 140.061,
|
| 674 |
+
"step": 90000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.02,
|
| 678 |
+
"learning_rate": 1.321032055817767e-05,
|
| 679 |
+
"loss": 0.2824,
|
| 680 |
+
"step": 91000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.04,
|
| 684 |
+
"learning_rate": 1.2540659232313314e-05,
|
| 685 |
+
"loss": 0.2829,
|
| 686 |
+
"step": 92000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 1.05,
|
| 690 |
+
"learning_rate": 1.1947971893203618e-05,
|
| 691 |
+
"loss": 0.2831,
|
| 692 |
+
"step": 93000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.06,
|
| 696 |
+
"learning_rate": 1.1432934822396401e-05,
|
| 697 |
+
"loss": 0.2829,
|
| 698 |
+
"step": 94000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.07,
|
| 702 |
+
"learning_rate": 1.099613569916953e-05,
|
| 703 |
+
"loss": 0.283,
|
| 704 |
+
"step": 95000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.07,
|
| 708 |
+
"eval_runtime": 103.598,
|
| 709 |
+
"eval_samples_per_second": 1104.895,
|
| 710 |
+
"eval_steps_per_second": 138.12,
|
| 711 |
+
"step": 95000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.08,
|
| 715 |
+
"learning_rate": 1.0638072929963704e-05,
|
| 716 |
+
"loss": 0.2826,
|
| 717 |
+
"step": 96000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.09,
|
| 721 |
+
"learning_rate": 1.0359155079679535e-05,
|
| 722 |
+
"loss": 0.2822,
|
| 723 |
+
"step": 97000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.1,
|
| 727 |
+
"learning_rate": 1.0159700405487444e-05,
|
| 728 |
+
"loss": 0.2819,
|
| 729 |
+
"step": 98000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.11,
|
| 733 |
+
"learning_rate": 1.0039936493682776e-05,
|
| 734 |
+
"loss": 0.2821,
|
| 735 |
+
"step": 99000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.13,
|
| 739 |
+
"learning_rate": 1e-05,
|
| 740 |
+
"loss": 0.282,
|
| 741 |
+
"step": 100000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.13,
|
| 745 |
+
"eval_runtime": 105.072,
|
| 746 |
+
"eval_samples_per_second": 1089.396,
|
| 747 |
+
"eval_steps_per_second": 136.183,
|
| 748 |
+
"step": 100000
|
| 749 |
+
}
|
| 750 |
+
],
|
| 751 |
+
"max_steps": 100000,
|
| 752 |
+
"num_train_epochs": 2,
|
| 753 |
+
"total_flos": 3.843149702798031e+20,
|
| 754 |
+
"trial_name": null,
|
| 755 |
+
"trial_params": null
|
| 756 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69deeff8ef7b6144fb77f371c28ca9f38736e6ed63fd21d679b2d0d356c524e7
|
| 3 |
+
size 3576
|