update
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- trainer_state.json +622 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2ForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"pad_token_id": 50256,
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.18.0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6b00013af188ec4af78a9828472d1df3d951750b507f8cb33c463caa89fd2cd
|
| 3 |
+
size 510402855
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed8b1e7d7e12b7aa64da270fb0603e3f2261cb22d3d556adf53661dfecb9457
|
| 3 |
+
size 14439
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04f118ea3a586a7558b0bb7d0a43f7c8f5aceddd4fe5427b3b75c866a8ccb03d
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e9605933ce424c47ed5476ac734955c5186c45dfc859e224ba1528ed6195172
|
| 3 |
+
size 623
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 750000,
|
| 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": 1e-05,
|
| 13 |
+
"loss": 3.3081,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 9.83344888888889e-06,
|
| 19 |
+
"loss": 0.6857,
|
| 20 |
+
"step": 18750
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"eval_accuracy": 0.5564,
|
| 25 |
+
"eval_loss": 0.6798537373542786,
|
| 26 |
+
"eval_runtime": 9.7283,
|
| 27 |
+
"eval_samples_per_second": 1027.927,
|
| 28 |
+
"eval_steps_per_second": 16.138,
|
| 29 |
+
"step": 18750
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.1,
|
| 33 |
+
"learning_rate": 9.666862222222223e-06,
|
| 34 |
+
"loss": 0.6804,
|
| 35 |
+
"step": 37500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.1,
|
| 39 |
+
"eval_accuracy": 0.5607,
|
| 40 |
+
"eval_loss": 0.677202045917511,
|
| 41 |
+
"eval_runtime": 9.8699,
|
| 42 |
+
"eval_samples_per_second": 1013.18,
|
| 43 |
+
"eval_steps_per_second": 15.907,
|
| 44 |
+
"step": 37500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"learning_rate": 9.500275555555555e-06,
|
| 49 |
+
"loss": 0.679,
|
| 50 |
+
"step": 56250
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.15,
|
| 54 |
+
"eval_accuracy": 0.5559,
|
| 55 |
+
"eval_loss": 0.6789325475692749,
|
| 56 |
+
"eval_runtime": 9.7877,
|
| 57 |
+
"eval_samples_per_second": 1021.686,
|
| 58 |
+
"eval_steps_per_second": 16.04,
|
| 59 |
+
"step": 56250
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2,
|
| 63 |
+
"learning_rate": 9.33368888888889e-06,
|
| 64 |
+
"loss": 0.6785,
|
| 65 |
+
"step": 75000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2,
|
| 69 |
+
"eval_accuracy": 0.5639,
|
| 70 |
+
"eval_loss": 0.6760360598564148,
|
| 71 |
+
"eval_runtime": 9.8616,
|
| 72 |
+
"eval_samples_per_second": 1014.039,
|
| 73 |
+
"eval_steps_per_second": 15.92,
|
| 74 |
+
"step": 75000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.25,
|
| 78 |
+
"learning_rate": 9.167093333333335e-06,
|
| 79 |
+
"loss": 0.6777,
|
| 80 |
+
"step": 93750
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.25,
|
| 84 |
+
"eval_accuracy": 0.5672,
|
| 85 |
+
"eval_loss": 0.6752009987831116,
|
| 86 |
+
"eval_runtime": 9.8899,
|
| 87 |
+
"eval_samples_per_second": 1011.135,
|
| 88 |
+
"eval_steps_per_second": 15.875,
|
| 89 |
+
"step": 93750
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.3,
|
| 93 |
+
"learning_rate": 9.000515555555556e-06,
|
| 94 |
+
"loss": 0.6771,
|
| 95 |
+
"step": 112500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.3,
|
| 99 |
+
"eval_accuracy": 0.5647,
|
| 100 |
+
"eval_loss": 0.6761014461517334,
|
| 101 |
+
"eval_runtime": 9.9903,
|
| 102 |
+
"eval_samples_per_second": 1000.97,
|
| 103 |
+
"eval_steps_per_second": 15.715,
|
| 104 |
+
"step": 112500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.35,
|
| 108 |
+
"learning_rate": 8.833928888888889e-06,
|
| 109 |
+
"loss": 0.6765,
|
| 110 |
+
"step": 131250
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.35,
|
| 114 |
+
"eval_accuracy": 0.5665,
|
| 115 |
+
"eval_loss": 0.6758425235748291,
|
| 116 |
+
"eval_runtime": 9.7731,
|
| 117 |
+
"eval_samples_per_second": 1023.22,
|
| 118 |
+
"eval_steps_per_second": 16.065,
|
| 119 |
+
"step": 131250
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.4,
|
| 123 |
+
"learning_rate": 8.667333333333334e-06,
|
| 124 |
+
"loss": 0.6765,
|
| 125 |
+
"step": 150000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.4,
|
| 129 |
+
"eval_accuracy": 0.5669,
|
| 130 |
+
"eval_loss": 0.6743916869163513,
|
| 131 |
+
"eval_runtime": 9.7984,
|
| 132 |
+
"eval_samples_per_second": 1020.577,
|
| 133 |
+
"eval_steps_per_second": 16.023,
|
| 134 |
+
"step": 150000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.45,
|
| 138 |
+
"learning_rate": 8.50073777777778e-06,
|
| 139 |
+
"loss": 0.6762,
|
| 140 |
+
"step": 168750
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.45,
|
| 144 |
+
"eval_accuracy": 0.5682,
|
| 145 |
+
"eval_loss": 0.6749153137207031,
|
| 146 |
+
"eval_runtime": 9.9597,
|
| 147 |
+
"eval_samples_per_second": 1004.049,
|
| 148 |
+
"eval_steps_per_second": 15.764,
|
| 149 |
+
"step": 168750
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5,
|
| 153 |
+
"learning_rate": 8.334142222222223e-06,
|
| 154 |
+
"loss": 0.676,
|
| 155 |
+
"step": 187500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.5,
|
| 159 |
+
"eval_accuracy": 0.5673,
|
| 160 |
+
"eval_loss": 0.6741730570793152,
|
| 161 |
+
"eval_runtime": 9.9295,
|
| 162 |
+
"eval_samples_per_second": 1007.098,
|
| 163 |
+
"eval_steps_per_second": 15.811,
|
| 164 |
+
"step": 187500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.55,
|
| 168 |
+
"learning_rate": 8.167546666666666e-06,
|
| 169 |
+
"loss": 0.676,
|
| 170 |
+
"step": 206250
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.55,
|
| 174 |
+
"eval_accuracy": 0.5708,
|
| 175 |
+
"eval_loss": 0.6741572618484497,
|
| 176 |
+
"eval_runtime": 9.6873,
|
| 177 |
+
"eval_samples_per_second": 1032.278,
|
| 178 |
+
"eval_steps_per_second": 16.207,
|
| 179 |
+
"step": 206250
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.6,
|
| 183 |
+
"learning_rate": 8.000951111111112e-06,
|
| 184 |
+
"loss": 0.6758,
|
| 185 |
+
"step": 225000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.6,
|
| 189 |
+
"eval_accuracy": 0.569,
|
| 190 |
+
"eval_loss": 0.6750027537345886,
|
| 191 |
+
"eval_runtime": 10.218,
|
| 192 |
+
"eval_samples_per_second": 978.668,
|
| 193 |
+
"eval_steps_per_second": 15.365,
|
| 194 |
+
"step": 225000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.65,
|
| 198 |
+
"learning_rate": 7.834364444444446e-06,
|
| 199 |
+
"loss": 0.6755,
|
| 200 |
+
"step": 243750
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.65,
|
| 204 |
+
"eval_accuracy": 0.5688,
|
| 205 |
+
"eval_loss": 0.6740711331367493,
|
| 206 |
+
"eval_runtime": 10.1203,
|
| 207 |
+
"eval_samples_per_second": 988.117,
|
| 208 |
+
"eval_steps_per_second": 15.513,
|
| 209 |
+
"step": 243750
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.7,
|
| 213 |
+
"learning_rate": 7.66776e-06,
|
| 214 |
+
"loss": 0.6758,
|
| 215 |
+
"step": 262500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.7,
|
| 219 |
+
"eval_accuracy": 0.5676,
|
| 220 |
+
"eval_loss": 0.6746249198913574,
|
| 221 |
+
"eval_runtime": 9.7352,
|
| 222 |
+
"eval_samples_per_second": 1027.2,
|
| 223 |
+
"eval_steps_per_second": 16.127,
|
| 224 |
+
"step": 262500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.75,
|
| 228 |
+
"learning_rate": 7.501173333333334e-06,
|
| 229 |
+
"loss": 0.6754,
|
| 230 |
+
"step": 281250
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.75,
|
| 234 |
+
"eval_accuracy": 0.5728,
|
| 235 |
+
"eval_loss": 0.673089861869812,
|
| 236 |
+
"eval_runtime": 9.866,
|
| 237 |
+
"eval_samples_per_second": 1013.582,
|
| 238 |
+
"eval_steps_per_second": 15.913,
|
| 239 |
+
"step": 281250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.8,
|
| 243 |
+
"learning_rate": 7.334586666666668e-06,
|
| 244 |
+
"loss": 0.6752,
|
| 245 |
+
"step": 300000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.8,
|
| 249 |
+
"eval_accuracy": 0.5678,
|
| 250 |
+
"eval_loss": 0.6737684607505798,
|
| 251 |
+
"eval_runtime": 10.0756,
|
| 252 |
+
"eval_samples_per_second": 992.497,
|
| 253 |
+
"eval_steps_per_second": 15.582,
|
| 254 |
+
"step": 300000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.85,
|
| 258 |
+
"learning_rate": 7.167982222222223e-06,
|
| 259 |
+
"loss": 0.6753,
|
| 260 |
+
"step": 318750
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.85,
|
| 264 |
+
"eval_accuracy": 0.5744,
|
| 265 |
+
"eval_loss": 0.6733357310295105,
|
| 266 |
+
"eval_runtime": 9.7112,
|
| 267 |
+
"eval_samples_per_second": 1029.741,
|
| 268 |
+
"eval_steps_per_second": 16.167,
|
| 269 |
+
"step": 318750
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.9,
|
| 273 |
+
"learning_rate": 7.0013777777777784e-06,
|
| 274 |
+
"loss": 0.6752,
|
| 275 |
+
"step": 337500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9,
|
| 279 |
+
"eval_accuracy": 0.5692,
|
| 280 |
+
"eval_loss": 0.6732030510902405,
|
| 281 |
+
"eval_runtime": 9.8389,
|
| 282 |
+
"eval_samples_per_second": 1016.377,
|
| 283 |
+
"eval_steps_per_second": 15.957,
|
| 284 |
+
"step": 337500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.95,
|
| 288 |
+
"learning_rate": 6.834764444444445e-06,
|
| 289 |
+
"loss": 0.6753,
|
| 290 |
+
"step": 356250
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.95,
|
| 294 |
+
"eval_accuracy": 0.5714,
|
| 295 |
+
"eval_loss": 0.6738024950027466,
|
| 296 |
+
"eval_runtime": 9.6915,
|
| 297 |
+
"eval_samples_per_second": 1031.834,
|
| 298 |
+
"eval_steps_per_second": 16.2,
|
| 299 |
+
"step": 356250
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0,
|
| 303 |
+
"learning_rate": 6.66816888888889e-06,
|
| 304 |
+
"loss": 0.6749,
|
| 305 |
+
"step": 375000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.0,
|
| 309 |
+
"eval_accuracy": 0.5711,
|
| 310 |
+
"eval_loss": 0.6741089820861816,
|
| 311 |
+
"eval_runtime": 10.1172,
|
| 312 |
+
"eval_samples_per_second": 988.413,
|
| 313 |
+
"eval_steps_per_second": 15.518,
|
| 314 |
+
"step": 375000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.05,
|
| 318 |
+
"learning_rate": 6.501564444444445e-06,
|
| 319 |
+
"loss": 0.6732,
|
| 320 |
+
"step": 393750
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.05,
|
| 324 |
+
"eval_accuracy": 0.572,
|
| 325 |
+
"eval_loss": 0.6729293465614319,
|
| 326 |
+
"eval_runtime": 9.7745,
|
| 327 |
+
"eval_samples_per_second": 1023.073,
|
| 328 |
+
"eval_steps_per_second": 16.062,
|
| 329 |
+
"step": 393750
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.1,
|
| 333 |
+
"learning_rate": 6.33496e-06,
|
| 334 |
+
"loss": 0.6734,
|
| 335 |
+
"step": 412500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.1,
|
| 339 |
+
"eval_accuracy": 0.5715,
|
| 340 |
+
"eval_loss": 0.6731555461883545,
|
| 341 |
+
"eval_runtime": 9.9359,
|
| 342 |
+
"eval_samples_per_second": 1006.454,
|
| 343 |
+
"eval_steps_per_second": 15.801,
|
| 344 |
+
"step": 412500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.15,
|
| 348 |
+
"learning_rate": 6.168355555555556e-06,
|
| 349 |
+
"loss": 0.6733,
|
| 350 |
+
"step": 431250
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.15,
|
| 354 |
+
"eval_accuracy": 0.5726,
|
| 355 |
+
"eval_loss": 0.6726440191268921,
|
| 356 |
+
"eval_runtime": 9.7596,
|
| 357 |
+
"eval_samples_per_second": 1024.628,
|
| 358 |
+
"eval_steps_per_second": 16.087,
|
| 359 |
+
"step": 431250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.2,
|
| 363 |
+
"learning_rate": 6.001751111111111e-06,
|
| 364 |
+
"loss": 0.6734,
|
| 365 |
+
"step": 450000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.2,
|
| 369 |
+
"eval_accuracy": 0.5725,
|
| 370 |
+
"eval_loss": 0.6719476580619812,
|
| 371 |
+
"eval_runtime": 10.1776,
|
| 372 |
+
"eval_samples_per_second": 982.551,
|
| 373 |
+
"eval_steps_per_second": 15.426,
|
| 374 |
+
"step": 450000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.25,
|
| 378 |
+
"learning_rate": 5.8351555555555565e-06,
|
| 379 |
+
"loss": 0.6732,
|
| 380 |
+
"step": 468750
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.25,
|
| 384 |
+
"eval_accuracy": 0.5721,
|
| 385 |
+
"eval_loss": 0.6720800995826721,
|
| 386 |
+
"eval_runtime": 9.8195,
|
| 387 |
+
"eval_samples_per_second": 1018.38,
|
| 388 |
+
"eval_steps_per_second": 15.989,
|
| 389 |
+
"step": 468750
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.3,
|
| 393 |
+
"learning_rate": 5.668542222222223e-06,
|
| 394 |
+
"loss": 0.6732,
|
| 395 |
+
"step": 487500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3,
|
| 399 |
+
"eval_accuracy": 0.5719,
|
| 400 |
+
"eval_loss": 0.6730443239212036,
|
| 401 |
+
"eval_runtime": 9.8464,
|
| 402 |
+
"eval_samples_per_second": 1015.602,
|
| 403 |
+
"eval_steps_per_second": 15.945,
|
| 404 |
+
"step": 487500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.35,
|
| 408 |
+
"learning_rate": 5.501928888888889e-06,
|
| 409 |
+
"loss": 0.6732,
|
| 410 |
+
"step": 506250
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.35,
|
| 414 |
+
"eval_accuracy": 0.5731,
|
| 415 |
+
"eval_loss": 0.67209392786026,
|
| 416 |
+
"eval_runtime": 9.9162,
|
| 417 |
+
"eval_samples_per_second": 1008.449,
|
| 418 |
+
"eval_steps_per_second": 15.833,
|
| 419 |
+
"step": 506250
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.4,
|
| 423 |
+
"learning_rate": 5.335342222222223e-06,
|
| 424 |
+
"loss": 0.6733,
|
| 425 |
+
"step": 525000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.4,
|
| 429 |
+
"eval_accuracy": 0.5715,
|
| 430 |
+
"eval_loss": 0.6724963188171387,
|
| 431 |
+
"eval_runtime": 9.8765,
|
| 432 |
+
"eval_samples_per_second": 1012.507,
|
| 433 |
+
"eval_steps_per_second": 15.896,
|
| 434 |
+
"step": 525000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.45,
|
| 438 |
+
"learning_rate": 5.168737777777778e-06,
|
| 439 |
+
"loss": 0.6733,
|
| 440 |
+
"step": 543750
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.45,
|
| 444 |
+
"eval_accuracy": 0.5757,
|
| 445 |
+
"eval_loss": 0.6714832186698914,
|
| 446 |
+
"eval_runtime": 10.1309,
|
| 447 |
+
"eval_samples_per_second": 987.074,
|
| 448 |
+
"eval_steps_per_second": 15.497,
|
| 449 |
+
"step": 543750
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.5,
|
| 453 |
+
"learning_rate": 5.002133333333333e-06,
|
| 454 |
+
"loss": 0.673,
|
| 455 |
+
"step": 562500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.5,
|
| 459 |
+
"eval_accuracy": 0.5762,
|
| 460 |
+
"eval_loss": 0.6717364192008972,
|
| 461 |
+
"eval_runtime": 9.8941,
|
| 462 |
+
"eval_samples_per_second": 1010.706,
|
| 463 |
+
"eval_steps_per_second": 15.868,
|
| 464 |
+
"step": 562500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.55,
|
| 468 |
+
"learning_rate": 4.835546666666668e-06,
|
| 469 |
+
"loss": 0.6732,
|
| 470 |
+
"step": 581250
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.55,
|
| 474 |
+
"eval_accuracy": 0.5735,
|
| 475 |
+
"eval_loss": 0.672535240650177,
|
| 476 |
+
"eval_runtime": 9.8695,
|
| 477 |
+
"eval_samples_per_second": 1013.226,
|
| 478 |
+
"eval_steps_per_second": 15.908,
|
| 479 |
+
"step": 581250
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.6,
|
| 483 |
+
"learning_rate": 4.668942222222223e-06,
|
| 484 |
+
"loss": 0.6733,
|
| 485 |
+
"step": 600000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.6,
|
| 489 |
+
"eval_accuracy": 0.5729,
|
| 490 |
+
"eval_loss": 0.6723589897155762,
|
| 491 |
+
"eval_runtime": 9.9575,
|
| 492 |
+
"eval_samples_per_second": 1004.27,
|
| 493 |
+
"eval_steps_per_second": 15.767,
|
| 494 |
+
"step": 600000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.65,
|
| 498 |
+
"learning_rate": 4.502346666666667e-06,
|
| 499 |
+
"loss": 0.6729,
|
| 500 |
+
"step": 618750
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.65,
|
| 504 |
+
"eval_accuracy": 0.5714,
|
| 505 |
+
"eval_loss": 0.6716250777244568,
|
| 506 |
+
"eval_runtime": 10.0075,
|
| 507 |
+
"eval_samples_per_second": 999.255,
|
| 508 |
+
"eval_steps_per_second": 15.688,
|
| 509 |
+
"step": 618750
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.7,
|
| 513 |
+
"learning_rate": 4.335742222222223e-06,
|
| 514 |
+
"loss": 0.6729,
|
| 515 |
+
"step": 637500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.7,
|
| 519 |
+
"eval_accuracy": 0.576,
|
| 520 |
+
"eval_loss": 0.6714919805526733,
|
| 521 |
+
"eval_runtime": 9.9861,
|
| 522 |
+
"eval_samples_per_second": 1001.39,
|
| 523 |
+
"eval_steps_per_second": 15.722,
|
| 524 |
+
"step": 637500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.75,
|
| 528 |
+
"learning_rate": 4.169155555555556e-06,
|
| 529 |
+
"loss": 0.6726,
|
| 530 |
+
"step": 656250
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.75,
|
| 534 |
+
"eval_accuracy": 0.5785,
|
| 535 |
+
"eval_loss": 0.6716631054878235,
|
| 536 |
+
"eval_runtime": 9.8047,
|
| 537 |
+
"eval_samples_per_second": 1019.923,
|
| 538 |
+
"eval_steps_per_second": 16.013,
|
| 539 |
+
"step": 656250
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.8,
|
| 543 |
+
"learning_rate": 4.00256e-06,
|
| 544 |
+
"loss": 0.6723,
|
| 545 |
+
"step": 675000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.8,
|
| 549 |
+
"eval_accuracy": 0.5791,
|
| 550 |
+
"eval_loss": 0.6703997850418091,
|
| 551 |
+
"eval_runtime": 9.8558,
|
| 552 |
+
"eval_samples_per_second": 1014.636,
|
| 553 |
+
"eval_steps_per_second": 15.93,
|
| 554 |
+
"step": 675000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.85,
|
| 558 |
+
"learning_rate": 3.835955555555556e-06,
|
| 559 |
+
"loss": 0.6728,
|
| 560 |
+
"step": 693750
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.85,
|
| 564 |
+
"eval_accuracy": 0.5763,
|
| 565 |
+
"eval_loss": 0.6714270710945129,
|
| 566 |
+
"eval_runtime": 9.7423,
|
| 567 |
+
"eval_samples_per_second": 1026.453,
|
| 568 |
+
"eval_steps_per_second": 16.115,
|
| 569 |
+
"step": 693750
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.9,
|
| 573 |
+
"learning_rate": 3.6693511111111114e-06,
|
| 574 |
+
"loss": 0.6724,
|
| 575 |
+
"step": 712500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.9,
|
| 579 |
+
"eval_accuracy": 0.5795,
|
| 580 |
+
"eval_loss": 0.6705731749534607,
|
| 581 |
+
"eval_runtime": 10.1221,
|
| 582 |
+
"eval_samples_per_second": 987.933,
|
| 583 |
+
"eval_steps_per_second": 15.511,
|
| 584 |
+
"step": 712500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.95,
|
| 588 |
+
"learning_rate": 3.502746666666667e-06,
|
| 589 |
+
"loss": 0.6724,
|
| 590 |
+
"step": 731250
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.95,
|
| 594 |
+
"eval_accuracy": 0.5789,
|
| 595 |
+
"eval_loss": 0.6716538071632385,
|
| 596 |
+
"eval_runtime": 9.891,
|
| 597 |
+
"eval_samples_per_second": 1011.024,
|
| 598 |
+
"eval_steps_per_second": 15.873,
|
| 599 |
+
"step": 731250
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.0,
|
| 603 |
+
"learning_rate": 3.3361422222222222e-06,
|
| 604 |
+
"loss": 0.6727,
|
| 605 |
+
"step": 750000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.0,
|
| 609 |
+
"eval_accuracy": 0.5789,
|
| 610 |
+
"eval_loss": 0.6710340976715088,
|
| 611 |
+
"eval_runtime": 9.6333,
|
| 612 |
+
"eval_samples_per_second": 1038.067,
|
| 613 |
+
"eval_steps_per_second": 16.298,
|
| 614 |
+
"step": 750000
|
| 615 |
+
}
|
| 616 |
+
],
|
| 617 |
+
"max_steps": 1125000,
|
| 618 |
+
"num_train_epochs": 3,
|
| 619 |
+
"total_flos": 1.2542244576561201e+19,
|
| 620 |
+
"trial_name": null,
|
| 621 |
+
"trial_params": null
|
| 622 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfcf60947144714c74908273507f787eab62993c8fbfbd4d26bdda4e822569a5
|
| 3 |
+
size 3119
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|