Training in progress, step 5000
Browse files- .gitignore +1 -0
- config.json +31 -0
- last-checkpoint/config.json +31 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +696 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Nadav/PretrainedPHD-v5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PIXELForPreTraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"decoder_hidden_size": 512,
|
| 8 |
+
"decoder_intermediate_size": 2048,
|
| 9 |
+
"decoder_num_attention_heads": 16,
|
| 10 |
+
"decoder_num_hidden_layers": 8,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"image_size": [
|
| 15 |
+
368,
|
| 16 |
+
368
|
| 17 |
+
],
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"mask_ratio": 0.29,
|
| 22 |
+
"model_type": "pixel",
|
| 23 |
+
"norm_pix_loss": true,
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"qkv_bias": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.17.0"
|
| 31 |
+
}
|
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Nadav/PretrainedPHD-v5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PIXELForPreTraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"decoder_hidden_size": 512,
|
| 8 |
+
"decoder_intermediate_size": 2048,
|
| 9 |
+
"decoder_num_attention_heads": 16,
|
| 10 |
+
"decoder_num_hidden_layers": 8,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"image_size": [
|
| 15 |
+
368,
|
| 16 |
+
368
|
| 17 |
+
],
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"mask_ratio": 0.29,
|
| 22 |
+
"model_type": "pixel",
|
| 23 |
+
"norm_pix_loss": true,
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"qkv_bias": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.17.0"
|
| 31 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07a898657c45370f07abb4ab4d1c8e876febd1bf609116926a162069e1a47970
|
| 3 |
+
size 893438545
|
last-checkpoint/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4223272d72d98a1b1000328bcf5358687544620dcdd1e47df404ab0b76aa7f49
|
| 3 |
+
size 449471589
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b74e3551ea251157a08b95bc5994c1db39e75018963981970f89b9fa818a312d
|
| 3 |
+
size 21643
|
last-checkpoint/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5df0168a751b1257361283b5aa0c288d7c712011edfd861c618859611a2278ec
|
| 3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6725b8bc8877559167a2f507838e32cb00ce6e523a55845add6681cef66305d
|
| 3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,696 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.32396008811714394,
|
| 5 |
+
"global_step": 5000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 7.499997433903193e-05,
|
| 13 |
+
"loss": 0.5643,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 7.499988138223165e-05,
|
| 19 |
+
"loss": 0.5529,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 7.499972055242145e-05,
|
| 25 |
+
"loss": 0.5538,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 7.49994918499372e-05,
|
| 31 |
+
"loss": 0.5724,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.02,
|
| 36 |
+
"learning_rate": 7.49991952752565e-05,
|
| 37 |
+
"loss": 0.5788,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 7.499882215248722e-05,
|
| 43 |
+
"loss": 0.5781,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"learning_rate": 7.499838835997051e-05,
|
| 49 |
+
"loss": 0.5718,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.03,
|
| 54 |
+
"learning_rate": 7.499788669756192e-05,
|
| 55 |
+
"loss": 0.5777,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.03,
|
| 60 |
+
"learning_rate": 7.499733026908297e-05,
|
| 61 |
+
"loss": 0.5698,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.03,
|
| 66 |
+
"learning_rate": 7.499672340561472e-05,
|
| 67 |
+
"loss": 0.572,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.03,
|
| 72 |
+
"eval_loss": 0.5502374172210693,
|
| 73 |
+
"eval_runtime": 54.5197,
|
| 74 |
+
"eval_samples_per_second": 91.71,
|
| 75 |
+
"eval_steps_per_second": 0.734,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.04,
|
| 80 |
+
"learning_rate": 7.499595841661423e-05,
|
| 81 |
+
"loss": 0.5786,
|
| 82 |
+
"step": 550
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.04,
|
| 86 |
+
"learning_rate": 7.499525386224346e-05,
|
| 87 |
+
"loss": 0.5742,
|
| 88 |
+
"step": 600
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04,
|
| 92 |
+
"learning_rate": 7.499439835481834e-05,
|
| 93 |
+
"loss": 0.5764,
|
| 94 |
+
"step": 650
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05,
|
| 98 |
+
"learning_rate": 7.499349245048099e-05,
|
| 99 |
+
"loss": 0.5746,
|
| 100 |
+
"step": 700
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.05,
|
| 104 |
+
"learning_rate": 7.499254057681529e-05,
|
| 105 |
+
"loss": 0.5705,
|
| 106 |
+
"step": 750
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.05,
|
| 110 |
+
"learning_rate": 7.49915237637348e-05,
|
| 111 |
+
"loss": 0.5773,
|
| 112 |
+
"step": 800
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.06,
|
| 116 |
+
"learning_rate": 7.499046675764822e-05,
|
| 117 |
+
"loss": 0.5737,
|
| 118 |
+
"step": 850
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.06,
|
| 122 |
+
"learning_rate": 7.498932151494505e-05,
|
| 123 |
+
"loss": 0.5737,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.06,
|
| 128 |
+
"learning_rate": 7.498813893748129e-05,
|
| 129 |
+
"loss": 0.5745,
|
| 130 |
+
"step": 950
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.06,
|
| 134 |
+
"learning_rate": 7.498686527410858e-05,
|
| 135 |
+
"loss": 0.5638,
|
| 136 |
+
"step": 1000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.06,
|
| 140 |
+
"eval_loss": 0.5501351356506348,
|
| 141 |
+
"eval_runtime": 28.6578,
|
| 142 |
+
"eval_samples_per_second": 174.473,
|
| 143 |
+
"eval_steps_per_second": 1.396,
|
| 144 |
+
"step": 1000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.07,
|
| 148 |
+
"learning_rate": 7.498543513474516e-05,
|
| 149 |
+
"loss": 0.5785,
|
| 150 |
+
"step": 1050
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.07,
|
| 154 |
+
"learning_rate": 7.498402728964193e-05,
|
| 155 |
+
"loss": 0.5733,
|
| 156 |
+
"step": 1100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.07,
|
| 160 |
+
"learning_rate": 7.498252105660386e-05,
|
| 161 |
+
"loss": 0.5768,
|
| 162 |
+
"step": 1150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.08,
|
| 166 |
+
"learning_rate": 7.49810517112758e-05,
|
| 167 |
+
"loss": 0.5677,
|
| 168 |
+
"step": 1200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.08,
|
| 172 |
+
"learning_rate": 7.497937788112959e-05,
|
| 173 |
+
"loss": 0.5758,
|
| 174 |
+
"step": 1250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.08,
|
| 178 |
+
"learning_rate": 7.497782220551389e-05,
|
| 179 |
+
"loss": 0.5735,
|
| 180 |
+
"step": 1300
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.09,
|
| 184 |
+
"learning_rate": 7.497601428893868e-05,
|
| 185 |
+
"loss": 0.5673,
|
| 186 |
+
"step": 1350
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.09,
|
| 190 |
+
"learning_rate": 7.497413556831251e-05,
|
| 191 |
+
"loss": 0.5764,
|
| 192 |
+
"step": 1400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.09,
|
| 196 |
+
"learning_rate": 7.497222826402937e-05,
|
| 197 |
+
"loss": 0.5759,
|
| 198 |
+
"step": 1450
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1,
|
| 202 |
+
"learning_rate": 7.497020945398975e-05,
|
| 203 |
+
"loss": 0.5789,
|
| 204 |
+
"step": 1500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.1,
|
| 208 |
+
"eval_loss": 0.5501341819763184,
|
| 209 |
+
"eval_runtime": 33.7038,
|
| 210 |
+
"eval_samples_per_second": 148.351,
|
| 211 |
+
"eval_steps_per_second": 1.187,
|
| 212 |
+
"step": 1500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.1,
|
| 216 |
+
"learning_rate": 7.496811985255485e-05,
|
| 217 |
+
"loss": 0.5698,
|
| 218 |
+
"step": 1550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.1,
|
| 222 |
+
"learning_rate": 7.496581916390981e-05,
|
| 223 |
+
"loss": 0.5775,
|
| 224 |
+
"step": 1600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.11,
|
| 228 |
+
"learning_rate": 7.49646863792875e-05,
|
| 229 |
+
"loss": 0.5545,
|
| 230 |
+
"step": 1650
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.11,
|
| 234 |
+
"learning_rate": 7.496226713556832e-05,
|
| 235 |
+
"loss": 0.0,
|
| 236 |
+
"step": 1700
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.11,
|
| 240 |
+
"learning_rate": 7.495976779443197e-05,
|
| 241 |
+
"loss": 0.0,
|
| 242 |
+
"step": 1750
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.12,
|
| 246 |
+
"learning_rate": 7.495718836204532e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 1800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12,
|
| 252 |
+
"learning_rate": 7.495452884477285e-05,
|
| 253 |
+
"loss": 0.0,
|
| 254 |
+
"step": 1850
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.12,
|
| 258 |
+
"learning_rate": 7.495178924917667e-05,
|
| 259 |
+
"loss": 0.0,
|
| 260 |
+
"step": 1900
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.13,
|
| 264 |
+
"learning_rate": 7.494896958201646e-05,
|
| 265 |
+
"loss": 0.0,
|
| 266 |
+
"step": 1950
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.13,
|
| 270 |
+
"learning_rate": 7.494606985024944e-05,
|
| 271 |
+
"loss": 0.0,
|
| 272 |
+
"step": 2000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.13,
|
| 276 |
+
"eval_loss": NaN,
|
| 277 |
+
"eval_runtime": 31.9835,
|
| 278 |
+
"eval_samples_per_second": 156.331,
|
| 279 |
+
"eval_steps_per_second": 1.251,
|
| 280 |
+
"step": 2000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.13,
|
| 284 |
+
"learning_rate": 7.494309006103046e-05,
|
| 285 |
+
"loss": 0.0,
|
| 286 |
+
"step": 2050
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.14,
|
| 290 |
+
"learning_rate": 7.494003022171182e-05,
|
| 291 |
+
"loss": 0.0,
|
| 292 |
+
"step": 2100
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.14,
|
| 296 |
+
"learning_rate": 7.493689033984337e-05,
|
| 297 |
+
"loss": 0.0,
|
| 298 |
+
"step": 2150
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.14,
|
| 302 |
+
"learning_rate": 7.493367042317246e-05,
|
| 303 |
+
"loss": 0.0,
|
| 304 |
+
"step": 2200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.15,
|
| 308 |
+
"learning_rate": 7.493037047964393e-05,
|
| 309 |
+
"loss": 0.0,
|
| 310 |
+
"step": 2250
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.15,
|
| 314 |
+
"learning_rate": 7.492699051740003e-05,
|
| 315 |
+
"loss": 0.0,
|
| 316 |
+
"step": 2300
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.15,
|
| 320 |
+
"learning_rate": 7.492353054478051e-05,
|
| 321 |
+
"loss": 0.0,
|
| 322 |
+
"step": 2350
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.16,
|
| 326 |
+
"learning_rate": 7.491999057032251e-05,
|
| 327 |
+
"loss": 0.0,
|
| 328 |
+
"step": 2400
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.16,
|
| 332 |
+
"learning_rate": 7.491637060276054e-05,
|
| 333 |
+
"loss": 0.0,
|
| 334 |
+
"step": 2450
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.16,
|
| 338 |
+
"learning_rate": 7.491267065102654e-05,
|
| 339 |
+
"loss": 0.0,
|
| 340 |
+
"step": 2500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.16,
|
| 344 |
+
"eval_loss": NaN,
|
| 345 |
+
"eval_runtime": 34.2723,
|
| 346 |
+
"eval_samples_per_second": 145.891,
|
| 347 |
+
"eval_steps_per_second": 1.167,
|
| 348 |
+
"step": 2500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.17,
|
| 352 |
+
"learning_rate": 7.490889072424974e-05,
|
| 353 |
+
"loss": 0.0,
|
| 354 |
+
"step": 2550
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.17,
|
| 358 |
+
"learning_rate": 7.490503083175676e-05,
|
| 359 |
+
"loss": 0.0,
|
| 360 |
+
"step": 2600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.17,
|
| 364 |
+
"learning_rate": 7.490109098307149e-05,
|
| 365 |
+
"loss": 0.0,
|
| 366 |
+
"step": 2650
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.17,
|
| 370 |
+
"learning_rate": 7.489707118791511e-05,
|
| 371 |
+
"loss": 0.0,
|
| 372 |
+
"step": 2700
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.18,
|
| 376 |
+
"learning_rate": 7.489297145620607e-05,
|
| 377 |
+
"loss": 0.0,
|
| 378 |
+
"step": 2750
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.18,
|
| 382 |
+
"learning_rate": 7.488879179806007e-05,
|
| 383 |
+
"loss": 0.0,
|
| 384 |
+
"step": 2800
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.18,
|
| 388 |
+
"learning_rate": 7.488453222378997e-05,
|
| 389 |
+
"loss": 0.0,
|
| 390 |
+
"step": 2850
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.19,
|
| 394 |
+
"learning_rate": 7.488019274390587e-05,
|
| 395 |
+
"loss": 0.0,
|
| 396 |
+
"step": 2900
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.19,
|
| 400 |
+
"learning_rate": 7.487577336911498e-05,
|
| 401 |
+
"loss": 0.0,
|
| 402 |
+
"step": 2950
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.19,
|
| 406 |
+
"learning_rate": 7.487127411032169e-05,
|
| 407 |
+
"loss": 0.0,
|
| 408 |
+
"step": 3000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.19,
|
| 412 |
+
"eval_loss": NaN,
|
| 413 |
+
"eval_runtime": 42.091,
|
| 414 |
+
"eval_samples_per_second": 118.79,
|
| 415 |
+
"eval_steps_per_second": 0.95,
|
| 416 |
+
"step": 3000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2,
|
| 420 |
+
"learning_rate": 7.486669497862746e-05,
|
| 421 |
+
"loss": 0.0,
|
| 422 |
+
"step": 3050
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.2,
|
| 426 |
+
"learning_rate": 7.486203598533086e-05,
|
| 427 |
+
"loss": 0.0,
|
| 428 |
+
"step": 3100
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.2,
|
| 432 |
+
"learning_rate": 7.485729714192747e-05,
|
| 433 |
+
"loss": 0.0,
|
| 434 |
+
"step": 3150
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.21,
|
| 438 |
+
"learning_rate": 7.485247846010992e-05,
|
| 439 |
+
"loss": 0.0,
|
| 440 |
+
"step": 3200
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.21,
|
| 444 |
+
"learning_rate": 7.484757995176785e-05,
|
| 445 |
+
"loss": 0.0,
|
| 446 |
+
"step": 3250
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.21,
|
| 450 |
+
"learning_rate": 7.484260162898783e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 3300
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.22,
|
| 456 |
+
"learning_rate": 7.483754350405336e-05,
|
| 457 |
+
"loss": 0.0,
|
| 458 |
+
"step": 3350
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22,
|
| 462 |
+
"learning_rate": 7.483240558944487e-05,
|
| 463 |
+
"loss": 0.0,
|
| 464 |
+
"step": 3400
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.22,
|
| 468 |
+
"learning_rate": 7.482718789783967e-05,
|
| 469 |
+
"loss": 0.0,
|
| 470 |
+
"step": 3450
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.23,
|
| 474 |
+
"learning_rate": 7.482189044211188e-05,
|
| 475 |
+
"loss": 0.0,
|
| 476 |
+
"step": 3500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.23,
|
| 480 |
+
"eval_loss": NaN,
|
| 481 |
+
"eval_runtime": 34.686,
|
| 482 |
+
"eval_samples_per_second": 144.151,
|
| 483 |
+
"eval_steps_per_second": 1.153,
|
| 484 |
+
"step": 3500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.23,
|
| 488 |
+
"learning_rate": 7.481651323533246e-05,
|
| 489 |
+
"loss": 0.0,
|
| 490 |
+
"step": 3550
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.23,
|
| 494 |
+
"learning_rate": 7.481105629076911e-05,
|
| 495 |
+
"loss": 0.0,
|
| 496 |
+
"step": 3600
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.24,
|
| 500 |
+
"learning_rate": 7.48055196218863e-05,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 3650
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.24,
|
| 506 |
+
"learning_rate": 7.479990324234524e-05,
|
| 507 |
+
"loss": 0.0,
|
| 508 |
+
"step": 3700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.24,
|
| 512 |
+
"learning_rate": 7.479420716600376e-05,
|
| 513 |
+
"loss": 0.0,
|
| 514 |
+
"step": 3750
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.25,
|
| 518 |
+
"learning_rate": 7.478843140691636e-05,
|
| 519 |
+
"loss": 0.0,
|
| 520 |
+
"step": 3800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.25,
|
| 524 |
+
"learning_rate": 7.478257597933418e-05,
|
| 525 |
+
"loss": 0.0,
|
| 526 |
+
"step": 3850
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.25,
|
| 530 |
+
"learning_rate": 7.477664089770488e-05,
|
| 531 |
+
"loss": 0.0,
|
| 532 |
+
"step": 3900
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.26,
|
| 536 |
+
"learning_rate": 7.477062617667268e-05,
|
| 537 |
+
"loss": 0.0,
|
| 538 |
+
"step": 3950
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.26,
|
| 542 |
+
"learning_rate": 7.476453183107833e-05,
|
| 543 |
+
"loss": 0.0,
|
| 544 |
+
"step": 4000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.26,
|
| 548 |
+
"eval_loss": NaN,
|
| 549 |
+
"eval_runtime": 30.491,
|
| 550 |
+
"eval_samples_per_second": 163.983,
|
| 551 |
+
"eval_steps_per_second": 1.312,
|
| 552 |
+
"step": 4000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.26,
|
| 556 |
+
"learning_rate": 7.4758357875959e-05,
|
| 557 |
+
"loss": 0.0,
|
| 558 |
+
"step": 4050
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.27,
|
| 562 |
+
"learning_rate": 7.475210432654833e-05,
|
| 563 |
+
"loss": 0.0,
|
| 564 |
+
"step": 4100
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.27,
|
| 568 |
+
"learning_rate": 7.474577119827632e-05,
|
| 569 |
+
"loss": 0.0,
|
| 570 |
+
"step": 4150
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.27,
|
| 574 |
+
"learning_rate": 7.473935850676932e-05,
|
| 575 |
+
"loss": 0.0,
|
| 576 |
+
"step": 4200
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.28,
|
| 580 |
+
"learning_rate": 7.473286626785004e-05,
|
| 581 |
+
"loss": 0.0,
|
| 582 |
+
"step": 4250
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.28,
|
| 586 |
+
"learning_rate": 7.472629449753742e-05,
|
| 587 |
+
"loss": 0.0,
|
| 588 |
+
"step": 4300
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.28,
|
| 592 |
+
"learning_rate": 7.471964321204664e-05,
|
| 593 |
+
"loss": 0.0,
|
| 594 |
+
"step": 4350
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.29,
|
| 598 |
+
"learning_rate": 7.47129124277891e-05,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 4400
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.29,
|
| 604 |
+
"learning_rate": 7.470610216137234e-05,
|
| 605 |
+
"loss": 0.0,
|
| 606 |
+
"step": 4450
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.29,
|
| 610 |
+
"learning_rate": 7.46992124296e-05,
|
| 611 |
+
"loss": 0.0,
|
| 612 |
+
"step": 4500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.29,
|
| 616 |
+
"eval_loss": NaN,
|
| 617 |
+
"eval_runtime": 39.5392,
|
| 618 |
+
"eval_samples_per_second": 126.457,
|
| 619 |
+
"eval_steps_per_second": 1.012,
|
| 620 |
+
"step": 4500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.29,
|
| 624 |
+
"learning_rate": 7.469224324947183e-05,
|
| 625 |
+
"loss": 0.0,
|
| 626 |
+
"step": 4550
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3,
|
| 630 |
+
"learning_rate": 7.468519463818356e-05,
|
| 631 |
+
"loss": 0.0,
|
| 632 |
+
"step": 4600
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.3,
|
| 636 |
+
"learning_rate": 7.467806661312698e-05,
|
| 637 |
+
"loss": 0.0,
|
| 638 |
+
"step": 4650
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.3,
|
| 642 |
+
"learning_rate": 7.467085919188974e-05,
|
| 643 |
+
"loss": 0.0,
|
| 644 |
+
"step": 4700
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.31,
|
| 648 |
+
"learning_rate": 7.466357239225546e-05,
|
| 649 |
+
"loss": 0.0,
|
| 650 |
+
"step": 4750
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.31,
|
| 654 |
+
"learning_rate": 7.46562062322036e-05,
|
| 655 |
+
"loss": 0.0,
|
| 656 |
+
"step": 4800
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.31,
|
| 660 |
+
"learning_rate": 7.46487607299094e-05,
|
| 661 |
+
"loss": 0.0,
|
| 662 |
+
"step": 4850
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.32,
|
| 666 |
+
"learning_rate": 7.464123590374392e-05,
|
| 667 |
+
"loss": 0.0,
|
| 668 |
+
"step": 4900
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.32,
|
| 672 |
+
"learning_rate": 7.463363177227392e-05,
|
| 673 |
+
"loss": 0.0,
|
| 674 |
+
"step": 4950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.32,
|
| 678 |
+
"learning_rate": 7.462594835426182e-05,
|
| 679 |
+
"loss": 0.0,
|
| 680 |
+
"step": 5000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.32,
|
| 684 |
+
"eval_loss": NaN,
|
| 685 |
+
"eval_runtime": 42.5393,
|
| 686 |
+
"eval_samples_per_second": 117.538,
|
| 687 |
+
"eval_steps_per_second": 0.94,
|
| 688 |
+
"step": 5000
|
| 689 |
+
}
|
| 690 |
+
],
|
| 691 |
+
"max_steps": 100000,
|
| 692 |
+
"num_train_epochs": 7,
|
| 693 |
+
"total_flos": 1.752506547830784e+20,
|
| 694 |
+
"trial_name": null,
|
| 695 |
+
"trial_params": null
|
| 696 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f335cbbefe437e0bdf4980f70b9fdc43c61baac005b22c2f5c6ae12bbb61c900
|
| 3 |
+
size 5615
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4223272d72d98a1b1000328bcf5358687544620dcdd1e47df404ab0b76aa7f49
|
| 3 |
+
size 449471589
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f335cbbefe437e0bdf4980f70b9fdc43c61baac005b22c2f5c6ae12bbb61c900
|
| 3 |
+
size 5615
|