Owen Huang
commited on
Commit
•
b38dad4
1
Parent(s):
0b8da5a
First commit
Browse files- checkpoint-23000/config.json +31 -0
- checkpoint-23000/optimizer.pt +3 -0
- checkpoint-23000/pytorch_model.bin +3 -0
- checkpoint-23000/rng_state_0.pth +3 -0
- checkpoint-23000/rng_state_1.pth +3 -0
- checkpoint-23000/rng_state_2.pth +3 -0
- checkpoint-23000/rng_state_3.pth +3 -0
- checkpoint-23000/scaler.pt +3 -0
- checkpoint-23000/scheduler.pt +3 -0
- checkpoint-23000/trainer_state.json +660 -0
- checkpoint-23000/training_args.bin +3 -0
- config.json +31 -0
- runs/Oct20_16-42-32_insilicotw01/1666255479.2338583/events.out.tfevents.1666255479.insilicotw01.2209970.1 +3 -0
- runs/Oct20_16-42-32_insilicotw01/events.out.tfevents.1666255479.insilicotw01.2209970.0 +3 -0
- runs/Oct20_16-56-12_insilicotw01/1666256182.2672875/events.out.tfevents.1666256182.insilicotw01.2258159.1 +3 -0
- runs/Oct20_16-56-12_insilicotw01/events.out.tfevents.1666256182.insilicotw01.2258159.0 +3 -0
- runs/Oct20_16-56-40_insilicotw01/1666256212.0382137/events.out.tfevents.1666256212.insilicotw01.2258159.3 +3 -0
- runs/Oct20_16-56-40_insilicotw01/1666258271.977599/events.out.tfevents.1666258271.insilicotw01.2258159.5 +3 -0
- runs/Oct20_16-56-40_insilicotw01/1666949707.5398886/events.out.tfevents.1666949707.insilicotw01.2258159.7 +3 -0
- runs/Oct20_16-56-40_insilicotw01/events.out.tfevents.1666256212.insilicotw01.2258159.2 +3 -0
- runs/Oct20_16-56-40_insilicotw01/events.out.tfevents.1666258271.insilicotw01.2258159.4 +3 -0
- runs/Oct20_16-56-40_insilicotw01/events.out.tfevents.1666949707.insilicotw01.2258159.6 +3 -0
- runs/Oct29_06-14-03_insilicotw01/1666995283.8650794/events.out.tfevents.1666995283.insilicotw01.938086.1 +3 -0
- runs/Oct29_06-14-03_insilicotw01/events.out.tfevents.1666995283.insilicotw01.938086.0 +3 -0
- runs/Oct29_06-32-16_insilicotw01/1666996353.394656/events.out.tfevents.1666996353.insilicotw01.938086.3 +3 -0
- runs/Oct29_06-32-16_insilicotw01/events.out.tfevents.1666996353.insilicotw01.938086.2 +3 -0
checkpoint-23000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 3,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.23.1",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 3121
|
| 31 |
+
}
|
checkpoint-23000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8e1317d7fb509dc62a56a33c23ac8f511f934032c5ace47b6bb374d75f6e55
|
| 3 |
+
size 706000433
|
checkpoint-23000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d0f255e90fbfe4ffefde91d36aef09b6ad9d4fcbb33f4bbbf1d3ced8d855485
|
| 3 |
+
size 365594729
|
checkpoint-23000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:932db2a7812856901d47dbd8bdf470e489b77cb85f3a45ac28f13f064a937517
|
| 3 |
+
size 14503
|
checkpoint-23000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:932db2a7812856901d47dbd8bdf470e489b77cb85f3a45ac28f13f064a937517
|
| 3 |
+
size 14503
|
checkpoint-23000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:932db2a7812856901d47dbd8bdf470e489b77cb85f3a45ac28f13f064a937517
|
| 3 |
+
size 14503
|
checkpoint-23000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:932db2a7812856901d47dbd8bdf470e489b77cb85f3a45ac28f13f064a937517
|
| 3 |
+
size 14503
|
checkpoint-23000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6f6bb9827d8048643eefdc61c104360ecd38cbb0b08488257564353e11d053e
|
| 3 |
+
size 559
|
checkpoint-23000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e1095c5b4157f5ab1f695d14c840892bf0cc26e52723f694f52ad962a76a67c
|
| 3 |
+
size 623
|
checkpoint-23000/trainer_state.json
ADDED
|
@@ -0,0 +1,660 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 98.2905982905983,
|
| 5 |
+
"global_step": 23000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.14,
|
| 12 |
+
"learning_rate": 4.8933760683760685e-05,
|
| 13 |
+
"loss": 1.1035,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.14,
|
| 18 |
+
"eval_loss": 0.7537529468536377,
|
| 19 |
+
"eval_runtime": 164.1555,
|
| 20 |
+
"eval_samples_per_second": 1072.605,
|
| 21 |
+
"eval_steps_per_second": 33.523,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 4.27,
|
| 26 |
+
"learning_rate": 4.7865384615384615e-05,
|
| 27 |
+
"loss": 0.7267,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 4.27,
|
| 32 |
+
"eval_loss": 0.6768979430198669,
|
| 33 |
+
"eval_runtime": 180.9639,
|
| 34 |
+
"eval_samples_per_second": 972.979,
|
| 35 |
+
"eval_steps_per_second": 30.409,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 6.41,
|
| 40 |
+
"learning_rate": 4.6797008547008546e-05,
|
| 41 |
+
"loss": 0.6744,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 6.41,
|
| 46 |
+
"eval_loss": 0.6488664746284485,
|
| 47 |
+
"eval_runtime": 190.376,
|
| 48 |
+
"eval_samples_per_second": 924.875,
|
| 49 |
+
"eval_steps_per_second": 28.906,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 8.55,
|
| 54 |
+
"learning_rate": 4.572863247863248e-05,
|
| 55 |
+
"loss": 0.6491,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 8.55,
|
| 60 |
+
"eval_loss": 0.6347554326057434,
|
| 61 |
+
"eval_runtime": 166.0432,
|
| 62 |
+
"eval_samples_per_second": 1060.411,
|
| 63 |
+
"eval_steps_per_second": 33.142,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 10.68,
|
| 68 |
+
"learning_rate": 4.466025641025641e-05,
|
| 69 |
+
"loss": 0.6334,
|
| 70 |
+
"step": 2500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 10.68,
|
| 74 |
+
"eval_loss": 0.6249234080314636,
|
| 75 |
+
"eval_runtime": 165.6169,
|
| 76 |
+
"eval_samples_per_second": 1063.141,
|
| 77 |
+
"eval_steps_per_second": 33.227,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 12.82,
|
| 82 |
+
"learning_rate": 4.359188034188034e-05,
|
| 83 |
+
"loss": 0.6219,
|
| 84 |
+
"step": 3000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 12.82,
|
| 88 |
+
"eval_loss": 0.6181825995445251,
|
| 89 |
+
"eval_runtime": 167.5877,
|
| 90 |
+
"eval_samples_per_second": 1050.638,
|
| 91 |
+
"eval_steps_per_second": 32.837,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 14.96,
|
| 96 |
+
"learning_rate": 4.252350427350428e-05,
|
| 97 |
+
"loss": 0.6131,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 14.96,
|
| 102 |
+
"eval_loss": 0.6141465902328491,
|
| 103 |
+
"eval_runtime": 177.8868,
|
| 104 |
+
"eval_samples_per_second": 989.809,
|
| 105 |
+
"eval_steps_per_second": 30.935,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 17.09,
|
| 110 |
+
"learning_rate": 4.145512820512821e-05,
|
| 111 |
+
"loss": 0.6058,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 17.09,
|
| 116 |
+
"eval_loss": 0.6131681203842163,
|
| 117 |
+
"eval_runtime": 163.4313,
|
| 118 |
+
"eval_samples_per_second": 1077.358,
|
| 119 |
+
"eval_steps_per_second": 33.672,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 19.23,
|
| 124 |
+
"learning_rate": 4.0386752136752134e-05,
|
| 125 |
+
"loss": 0.5995,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 19.23,
|
| 130 |
+
"eval_loss": 0.6094414591789246,
|
| 131 |
+
"eval_runtime": 178.3809,
|
| 132 |
+
"eval_samples_per_second": 987.068,
|
| 133 |
+
"eval_steps_per_second": 30.85,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 21.37,
|
| 138 |
+
"learning_rate": 3.931837606837607e-05,
|
| 139 |
+
"loss": 0.5941,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 21.37,
|
| 144 |
+
"eval_loss": 0.6074140667915344,
|
| 145 |
+
"eval_runtime": 169.9857,
|
| 146 |
+
"eval_samples_per_second": 1035.817,
|
| 147 |
+
"eval_steps_per_second": 32.373,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 23.5,
|
| 152 |
+
"learning_rate": 3.825e-05,
|
| 153 |
+
"loss": 0.5894,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 23.5,
|
| 158 |
+
"eval_loss": 0.6062588691711426,
|
| 159 |
+
"eval_runtime": 168.4324,
|
| 160 |
+
"eval_samples_per_second": 1045.369,
|
| 161 |
+
"eval_steps_per_second": 32.672,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 25.64,
|
| 166 |
+
"learning_rate": 3.718162393162393e-05,
|
| 167 |
+
"loss": 0.5851,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 25.64,
|
| 172 |
+
"eval_loss": 0.6049907207489014,
|
| 173 |
+
"eval_runtime": 169.165,
|
| 174 |
+
"eval_samples_per_second": 1040.842,
|
| 175 |
+
"eval_steps_per_second": 32.53,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 27.78,
|
| 180 |
+
"learning_rate": 3.611324786324787e-05,
|
| 181 |
+
"loss": 0.5813,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 27.78,
|
| 186 |
+
"eval_loss": 0.6046043634414673,
|
| 187 |
+
"eval_runtime": 164.2895,
|
| 188 |
+
"eval_samples_per_second": 1071.73,
|
| 189 |
+
"eval_steps_per_second": 33.496,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 29.91,
|
| 194 |
+
"learning_rate": 3.50448717948718e-05,
|
| 195 |
+
"loss": 0.5777,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 29.91,
|
| 200 |
+
"eval_loss": 0.6043672561645508,
|
| 201 |
+
"eval_runtime": 163.9442,
|
| 202 |
+
"eval_samples_per_second": 1073.987,
|
| 203 |
+
"eval_steps_per_second": 33.566,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 32.05,
|
| 208 |
+
"learning_rate": 3.397649572649573e-05,
|
| 209 |
+
"loss": 0.5744,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 32.05,
|
| 214 |
+
"eval_loss": 0.6073368787765503,
|
| 215 |
+
"eval_runtime": 182.0186,
|
| 216 |
+
"eval_samples_per_second": 967.341,
|
| 217 |
+
"eval_steps_per_second": 30.233,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 34.19,
|
| 222 |
+
"learning_rate": 3.290811965811966e-05,
|
| 223 |
+
"loss": 0.5712,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 34.19,
|
| 228 |
+
"eval_loss": 0.6060159802436829,
|
| 229 |
+
"eval_runtime": 164.583,
|
| 230 |
+
"eval_samples_per_second": 1069.819,
|
| 231 |
+
"eval_steps_per_second": 33.436,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 36.32,
|
| 236 |
+
"learning_rate": 3.183974358974359e-05,
|
| 237 |
+
"loss": 0.5684,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 36.32,
|
| 242 |
+
"eval_loss": 0.6061359643936157,
|
| 243 |
+
"eval_runtime": 165.5065,
|
| 244 |
+
"eval_samples_per_second": 1063.849,
|
| 245 |
+
"eval_steps_per_second": 33.249,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 38.46,
|
| 250 |
+
"learning_rate": 3.077136752136752e-05,
|
| 251 |
+
"loss": 0.5658,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 38.46,
|
| 256 |
+
"eval_loss": 0.6064005494117737,
|
| 257 |
+
"eval_runtime": 177.3855,
|
| 258 |
+
"eval_samples_per_second": 992.607,
|
| 259 |
+
"eval_steps_per_second": 31.023,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 40.6,
|
| 264 |
+
"learning_rate": 2.9702991452991454e-05,
|
| 265 |
+
"loss": 0.5634,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 40.6,
|
| 270 |
+
"eval_loss": 0.6069360375404358,
|
| 271 |
+
"eval_runtime": 164.0377,
|
| 272 |
+
"eval_samples_per_second": 1073.375,
|
| 273 |
+
"eval_steps_per_second": 33.547,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 42.74,
|
| 278 |
+
"learning_rate": 2.8634615384615387e-05,
|
| 279 |
+
"loss": 0.5612,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 42.74,
|
| 284 |
+
"eval_loss": 0.6074803471565247,
|
| 285 |
+
"eval_runtime": 184.5732,
|
| 286 |
+
"eval_samples_per_second": 953.952,
|
| 287 |
+
"eval_steps_per_second": 29.815,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 44.87,
|
| 292 |
+
"learning_rate": 2.7566239316239318e-05,
|
| 293 |
+
"loss": 0.5591,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 44.87,
|
| 298 |
+
"eval_loss": 0.6080661416053772,
|
| 299 |
+
"eval_runtime": 164.771,
|
| 300 |
+
"eval_samples_per_second": 1068.598,
|
| 301 |
+
"eval_steps_per_second": 33.398,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 47.01,
|
| 306 |
+
"learning_rate": 2.6497863247863248e-05,
|
| 307 |
+
"loss": 0.5571,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 47.01,
|
| 312 |
+
"eval_loss": 0.610197901725769,
|
| 313 |
+
"eval_runtime": 163.8142,
|
| 314 |
+
"eval_samples_per_second": 1074.84,
|
| 315 |
+
"eval_steps_per_second": 33.593,
|
| 316 |
+
"step": 11000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 49.15,
|
| 320 |
+
"learning_rate": 2.542948717948718e-05,
|
| 321 |
+
"loss": 0.5549,
|
| 322 |
+
"step": 11500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 49.15,
|
| 326 |
+
"eval_loss": 0.6111814379692078,
|
| 327 |
+
"eval_runtime": 172.4133,
|
| 328 |
+
"eval_samples_per_second": 1021.232,
|
| 329 |
+
"eval_steps_per_second": 31.917,
|
| 330 |
+
"step": 11500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 51.28,
|
| 334 |
+
"learning_rate": 2.4361111111111112e-05,
|
| 335 |
+
"loss": 0.5532,
|
| 336 |
+
"step": 12000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 51.28,
|
| 340 |
+
"eval_loss": 0.611818790435791,
|
| 341 |
+
"eval_runtime": 174.1127,
|
| 342 |
+
"eval_samples_per_second": 1011.264,
|
| 343 |
+
"eval_steps_per_second": 31.606,
|
| 344 |
+
"step": 12000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 53.42,
|
| 348 |
+
"learning_rate": 2.3292735042735045e-05,
|
| 349 |
+
"loss": 0.5515,
|
| 350 |
+
"step": 12500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 53.42,
|
| 354 |
+
"eval_loss": 0.6132317781448364,
|
| 355 |
+
"eval_runtime": 164.6297,
|
| 356 |
+
"eval_samples_per_second": 1069.515,
|
| 357 |
+
"eval_steps_per_second": 33.427,
|
| 358 |
+
"step": 12500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 55.56,
|
| 362 |
+
"learning_rate": 2.2224358974358976e-05,
|
| 363 |
+
"loss": 0.55,
|
| 364 |
+
"step": 13000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 55.56,
|
| 368 |
+
"eval_loss": 0.6136063933372498,
|
| 369 |
+
"eval_runtime": 164.5555,
|
| 370 |
+
"eval_samples_per_second": 1069.998,
|
| 371 |
+
"eval_steps_per_second": 33.442,
|
| 372 |
+
"step": 13000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 57.69,
|
| 376 |
+
"learning_rate": 2.1155982905982906e-05,
|
| 377 |
+
"loss": 0.5486,
|
| 378 |
+
"step": 13500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 57.69,
|
| 382 |
+
"eval_loss": 0.6144915819168091,
|
| 383 |
+
"eval_runtime": 203.4153,
|
| 384 |
+
"eval_samples_per_second": 865.589,
|
| 385 |
+
"eval_steps_per_second": 27.053,
|
| 386 |
+
"step": 13500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 59.83,
|
| 390 |
+
"learning_rate": 2.008760683760684e-05,
|
| 391 |
+
"loss": 0.5472,
|
| 392 |
+
"step": 14000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 59.83,
|
| 396 |
+
"eval_loss": 0.6147069931030273,
|
| 397 |
+
"eval_runtime": 199.2649,
|
| 398 |
+
"eval_samples_per_second": 883.618,
|
| 399 |
+
"eval_steps_per_second": 27.617,
|
| 400 |
+
"step": 14000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 61.97,
|
| 404 |
+
"learning_rate": 1.9021367521367522e-05,
|
| 405 |
+
"loss": 0.5457,
|
| 406 |
+
"step": 14500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 61.97,
|
| 410 |
+
"eval_loss": 0.6158111095428467,
|
| 411 |
+
"eval_runtime": 206.6245,
|
| 412 |
+
"eval_samples_per_second": 852.145,
|
| 413 |
+
"eval_steps_per_second": 26.633,
|
| 414 |
+
"step": 14500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 64.1,
|
| 418 |
+
"learning_rate": 1.7952991452991456e-05,
|
| 419 |
+
"loss": 0.5445,
|
| 420 |
+
"step": 15000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 64.1,
|
| 424 |
+
"eval_loss": 0.6180585026741028,
|
| 425 |
+
"eval_runtime": 181.3159,
|
| 426 |
+
"eval_samples_per_second": 971.09,
|
| 427 |
+
"eval_steps_per_second": 30.35,
|
| 428 |
+
"step": 15000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 66.24,
|
| 432 |
+
"learning_rate": 1.688675213675214e-05,
|
| 433 |
+
"loss": 0.5431,
|
| 434 |
+
"step": 15500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 66.24,
|
| 438 |
+
"eval_loss": 0.6186466217041016,
|
| 439 |
+
"eval_runtime": 175.3115,
|
| 440 |
+
"eval_samples_per_second": 1004.349,
|
| 441 |
+
"eval_steps_per_second": 31.39,
|
| 442 |
+
"step": 15500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 68.38,
|
| 446 |
+
"learning_rate": 1.581837606837607e-05,
|
| 447 |
+
"loss": 0.5421,
|
| 448 |
+
"step": 16000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 68.38,
|
| 452 |
+
"eval_loss": 0.6195328831672668,
|
| 453 |
+
"eval_runtime": 164.9282,
|
| 454 |
+
"eval_samples_per_second": 1067.58,
|
| 455 |
+
"eval_steps_per_second": 33.366,
|
| 456 |
+
"step": 16000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 70.51,
|
| 460 |
+
"learning_rate": 1.475e-05,
|
| 461 |
+
"loss": 0.5411,
|
| 462 |
+
"step": 16500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 70.51,
|
| 466 |
+
"eval_loss": 0.6201679110527039,
|
| 467 |
+
"eval_runtime": 197.124,
|
| 468 |
+
"eval_samples_per_second": 893.215,
|
| 469 |
+
"eval_steps_per_second": 27.916,
|
| 470 |
+
"step": 16500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 72.65,
|
| 474 |
+
"learning_rate": 1.3681623931623933e-05,
|
| 475 |
+
"loss": 0.5401,
|
| 476 |
+
"step": 17000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 72.65,
|
| 480 |
+
"eval_loss": 0.6210618019104004,
|
| 481 |
+
"eval_runtime": 173.1765,
|
| 482 |
+
"eval_samples_per_second": 1016.732,
|
| 483 |
+
"eval_steps_per_second": 31.777,
|
| 484 |
+
"step": 17000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 74.79,
|
| 488 |
+
"learning_rate": 1.2613247863247865e-05,
|
| 489 |
+
"loss": 0.5391,
|
| 490 |
+
"step": 17500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 74.79,
|
| 494 |
+
"eval_loss": 0.6214122772216797,
|
| 495 |
+
"eval_runtime": 196.4031,
|
| 496 |
+
"eval_samples_per_second": 896.493,
|
| 497 |
+
"eval_steps_per_second": 28.019,
|
| 498 |
+
"step": 17500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 76.92,
|
| 502 |
+
"learning_rate": 1.1544871794871795e-05,
|
| 503 |
+
"loss": 0.5382,
|
| 504 |
+
"step": 18000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 76.92,
|
| 508 |
+
"eval_loss": 0.6220324635505676,
|
| 509 |
+
"eval_runtime": 164.5331,
|
| 510 |
+
"eval_samples_per_second": 1070.143,
|
| 511 |
+
"eval_steps_per_second": 33.446,
|
| 512 |
+
"step": 18000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 79.06,
|
| 516 |
+
"learning_rate": 1.0476495726495727e-05,
|
| 517 |
+
"loss": 0.5372,
|
| 518 |
+
"step": 18500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 79.06,
|
| 522 |
+
"eval_loss": 0.6238572001457214,
|
| 523 |
+
"eval_runtime": 180.654,
|
| 524 |
+
"eval_samples_per_second": 974.647,
|
| 525 |
+
"eval_steps_per_second": 30.462,
|
| 526 |
+
"step": 18500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 81.2,
|
| 530 |
+
"learning_rate": 9.40811965811966e-06,
|
| 531 |
+
"loss": 0.5363,
|
| 532 |
+
"step": 19000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 81.2,
|
| 536 |
+
"eval_loss": 0.6245262026786804,
|
| 537 |
+
"eval_runtime": 163.6759,
|
| 538 |
+
"eval_samples_per_second": 1075.748,
|
| 539 |
+
"eval_steps_per_second": 33.621,
|
| 540 |
+
"step": 19000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 83.33,
|
| 544 |
+
"learning_rate": 8.341880341880342e-06,
|
| 545 |
+
"loss": 0.5355,
|
| 546 |
+
"step": 19500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 83.33,
|
| 550 |
+
"eval_loss": 0.6251608729362488,
|
| 551 |
+
"eval_runtime": 200.2426,
|
| 552 |
+
"eval_samples_per_second": 879.303,
|
| 553 |
+
"eval_steps_per_second": 27.482,
|
| 554 |
+
"step": 19500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 85.47,
|
| 558 |
+
"learning_rate": 7.273504273504274e-06,
|
| 559 |
+
"loss": 0.5348,
|
| 560 |
+
"step": 20000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 85.47,
|
| 564 |
+
"eval_loss": 0.6253054738044739,
|
| 565 |
+
"eval_runtime": 175.0233,
|
| 566 |
+
"eval_samples_per_second": 1006.003,
|
| 567 |
+
"eval_steps_per_second": 31.442,
|
| 568 |
+
"step": 20000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 87.61,
|
| 572 |
+
"learning_rate": 6.205128205128206e-06,
|
| 573 |
+
"loss": 0.5341,
|
| 574 |
+
"step": 20500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 87.61,
|
| 578 |
+
"eval_loss": 0.6260212063789368,
|
| 579 |
+
"eval_runtime": 165.1088,
|
| 580 |
+
"eval_samples_per_second": 1066.412,
|
| 581 |
+
"eval_steps_per_second": 33.33,
|
| 582 |
+
"step": 20500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 89.74,
|
| 586 |
+
"learning_rate": 5.136752136752137e-06,
|
| 587 |
+
"loss": 0.5334,
|
| 588 |
+
"step": 21000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 89.74,
|
| 592 |
+
"eval_loss": 0.6266852021217346,
|
| 593 |
+
"eval_runtime": 164.357,
|
| 594 |
+
"eval_samples_per_second": 1071.29,
|
| 595 |
+
"eval_steps_per_second": 33.482,
|
| 596 |
+
"step": 21000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 91.88,
|
| 600 |
+
"learning_rate": 4.068376068376069e-06,
|
| 601 |
+
"loss": 0.5327,
|
| 602 |
+
"step": 21500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 91.88,
|
| 606 |
+
"eval_loss": 0.6268437504768372,
|
| 607 |
+
"eval_runtime": 168.7818,
|
| 608 |
+
"eval_samples_per_second": 1043.205,
|
| 609 |
+
"eval_steps_per_second": 32.604,
|
| 610 |
+
"step": 21500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 94.02,
|
| 614 |
+
"learning_rate": 3e-06,
|
| 615 |
+
"loss": 0.5321,
|
| 616 |
+
"step": 22000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 94.02,
|
| 620 |
+
"eval_loss": 0.6274420022964478,
|
| 621 |
+
"eval_runtime": 193.8022,
|
| 622 |
+
"eval_samples_per_second": 908.524,
|
| 623 |
+
"eval_steps_per_second": 28.395,
|
| 624 |
+
"step": 22000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 96.15,
|
| 628 |
+
"learning_rate": 1.9316239316239316e-06,
|
| 629 |
+
"loss": 0.5315,
|
| 630 |
+
"step": 22500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 96.15,
|
| 634 |
+
"eval_loss": 0.6278537511825562,
|
| 635 |
+
"eval_runtime": 195.5578,
|
| 636 |
+
"eval_samples_per_second": 900.368,
|
| 637 |
+
"eval_steps_per_second": 28.14,
|
| 638 |
+
"step": 22500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 98.29,
|
| 642 |
+
"learning_rate": 8.632478632478633e-07,
|
| 643 |
+
"loss": 0.531,
|
| 644 |
+
"step": 23000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 98.29,
|
| 648 |
+
"eval_loss": 0.6279672980308533,
|
| 649 |
+
"eval_runtime": 167.092,
|
| 650 |
+
"eval_samples_per_second": 1053.755,
|
| 651 |
+
"eval_steps_per_second": 32.934,
|
| 652 |
+
"step": 23000
|
| 653 |
+
}
|
| 654 |
+
],
|
| 655 |
+
"max_steps": 23400,
|
| 656 |
+
"num_train_epochs": 100,
|
| 657 |
+
"total_flos": 2.3846898985745777e+18,
|
| 658 |
+
"trial_name": null,
|
| 659 |
+
"trial_params": null
|
| 660 |
+
}
|
checkpoint-23000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:037e99a910535424f9dbfbbbfc1fb709bfc8c9fed38418e890902813372e9e6a
|
| 3 |
+
size 3311
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.23.1",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 140
|
| 31 |
+
}
|
runs/Oct20_16-42-32_insilicotw01/1666255479.2338583/events.out.tfevents.1666255479.insilicotw01.2209970.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77fdbcea2c9e5a4be94d3e1c844c71c74e3a4d50432a93479039f38adea0ae41
|
| 3 |
+
size 5477
|
runs/Oct20_16-42-32_insilicotw01/events.out.tfevents.1666255479.insilicotw01.2209970.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e47baee02e6865574bb339568f81219a1036fb00f72c8a8e844e6eedd254f7e1
|
| 3 |
+
size 3738
|
runs/Oct20_16-56-12_insilicotw01/1666256182.2672875/events.out.tfevents.1666256182.insilicotw01.2258159.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcb5e4b80b81b468f2a9fa5b3825bb63261c226c5438d7bbd280c3add53552c5
|
| 3 |
+
size 5477
|
runs/Oct20_16-56-12_insilicotw01/events.out.tfevents.1666256182.insilicotw01.2258159.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9838fd123b69a96ca06b8dcd6a941f1e8d9021baa00cb0c660d3ae92a668e69b
|
| 3 |
+
size 3738
|
runs/Oct20_16-56-40_insilicotw01/1666256212.0382137/events.out.tfevents.1666256212.insilicotw01.2258159.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ac6be3d576a728c1679121ce76d24964ccad9319e86c5a965ce4c307fca1200
|
| 3 |
+
size 5480
|
runs/Oct20_16-56-40_insilicotw01/1666258271.977599/events.out.tfevents.1666258271.insilicotw01.2258159.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d48efaec4bc405ca30650ac50c27cb2b7944bcc06b377f0f64f7c79220bd23d0
|
| 3 |
+
size 5480
|
runs/Oct20_16-56-40_insilicotw01/1666949707.5398886/events.out.tfevents.1666949707.insilicotw01.2258159.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c05df1d2f343163b46eb24f0ac1d25c1a080e8ec8d6dfd19026f8e955079354c
|
| 3 |
+
size 5480
|
runs/Oct20_16-56-40_insilicotw01/events.out.tfevents.1666256212.insilicotw01.2258159.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e3363469df8e8773778ea6dec49dfd840ce5eb34381fc18041f760f8c6561dd
|
| 3 |
+
size 8602
|
runs/Oct20_16-56-40_insilicotw01/events.out.tfevents.1666258271.insilicotw01.2258159.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5c1b7b80e26269d05de4d8f3b09c388e90f178001fccf987bee9d3a6ca295f2
|
| 3 |
+
size 102375
|
runs/Oct20_16-56-40_insilicotw01/events.out.tfevents.1666949707.insilicotw01.2258159.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1f510300eebfb6f4bef4789180405969d480c80ebfd3632c4616ab7cb4cd32
|
| 3 |
+
size 4584
|
runs/Oct29_06-14-03_insilicotw01/1666995283.8650794/events.out.tfevents.1666995283.insilicotw01.938086.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27e9b02b928639b9501294f1305879090ff3c2ba54b0c3117d2fa3b11a39e1e0
|
| 3 |
+
size 5480
|
runs/Oct29_06-14-03_insilicotw01/events.out.tfevents.1666995283.insilicotw01.938086.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c33697a9d81c2f4fba0267d7ead5a9d7e2d00d61b57aa24e1e04917af42e18af
|
| 3 |
+
size 3728
|
runs/Oct29_06-32-16_insilicotw01/1666996353.394656/events.out.tfevents.1666996353.insilicotw01.938086.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:281762d051fb3a9f587f7560c8319516dbf36aa684a3047d77eb2329f60293a6
|
| 3 |
+
size 5480
|
runs/Oct29_06-32-16_insilicotw01/events.out.tfevents.1666996353.insilicotw01.938086.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f92a004ae0cf96cf70539fb799433cb3207bfa14864165b58ab3548bc7c5a23
|
| 3 |
+
size 3728
|