End of training
Browse files- README.md +3 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1030 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: google/long-t5-tglobal-xl
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: longt5_xl_sfd_bp_10
|
| 8 |
results: []
|
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# longt5_xl_sfd_bp_10
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 2.8921
|
| 19 |
|
|
|
|
| 3 |
base_model: google/long-t5-tglobal-xl
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- learn3r/summ_screen_fd_bp
|
| 8 |
model-index:
|
| 9 |
- name: longt5_xl_sfd_bp_10
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# longt5_xl_sfd_bp_10
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the learn3r/summ_screen_fd_bp dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 2.8921
|
| 21 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.48,
|
| 3 |
+
"eval_loss": 2.892078161239624,
|
| 4 |
+
"eval_runtime": 83.8687,
|
| 5 |
+
"eval_samples": 338,
|
| 6 |
+
"eval_samples_per_second": 4.03,
|
| 7 |
+
"eval_steps_per_second": 0.513,
|
| 8 |
+
"train_loss": 0.722327525381531,
|
| 9 |
+
"train_runtime": 70402.3599,
|
| 10 |
+
"train_samples": 3673,
|
| 11 |
+
"train_samples_per_second": 1.043,
|
| 12 |
+
"train_steps_per_second": 0.004
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.48,
|
| 3 |
+
"eval_loss": 2.892078161239624,
|
| 4 |
+
"eval_runtime": 83.8687,
|
| 5 |
+
"eval_samples": 338,
|
| 6 |
+
"eval_samples_per_second": 4.03,
|
| 7 |
+
"eval_steps_per_second": 0.513
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.48,
|
| 3 |
+
"train_loss": 0.722327525381531,
|
| 4 |
+
"train_runtime": 70402.3599,
|
| 5 |
+
"train_samples": 3673,
|
| 6 |
+
"train_samples_per_second": 1.043,
|
| 7 |
+
"train_steps_per_second": 0.004
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1030 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5011385679244995,
|
| 3 |
+
"best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_sfd_bp_10/checkpoint-43",
|
| 4 |
+
"epoch": 19.47826086956522,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 280,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14,
|
| 13 |
+
"learning_rate": 0.001,
|
| 14 |
+
"loss": 2.9672,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.28,
|
| 19 |
+
"learning_rate": 0.001,
|
| 20 |
+
"loss": 3.0162,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.42,
|
| 25 |
+
"learning_rate": 0.001,
|
| 26 |
+
"loss": 3.1689,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.56,
|
| 31 |
+
"learning_rate": 0.001,
|
| 32 |
+
"loss": 2.902,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.7,
|
| 37 |
+
"learning_rate": 0.001,
|
| 38 |
+
"loss": 2.4891,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.83,
|
| 43 |
+
"learning_rate": 0.001,
|
| 44 |
+
"loss": 2.8498,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.97,
|
| 49 |
+
"learning_rate": 0.001,
|
| 50 |
+
"loss": 2.3973,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.97,
|
| 55 |
+
"eval_loss": 1.9026896953582764,
|
| 56 |
+
"eval_runtime": 84.3252,
|
| 57 |
+
"eval_samples_per_second": 4.008,
|
| 58 |
+
"eval_steps_per_second": 0.51,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.11,
|
| 63 |
+
"learning_rate": 0.001,
|
| 64 |
+
"loss": 2.1921,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.25,
|
| 69 |
+
"learning_rate": 0.001,
|
| 70 |
+
"loss": 2.0091,
|
| 71 |
+
"step": 18
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.39,
|
| 75 |
+
"learning_rate": 0.001,
|
| 76 |
+
"loss": 1.8884,
|
| 77 |
+
"step": 20
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.53,
|
| 81 |
+
"learning_rate": 0.001,
|
| 82 |
+
"loss": 1.7955,
|
| 83 |
+
"step": 22
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.67,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"loss": 1.7023,
|
| 89 |
+
"step": 24
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.81,
|
| 93 |
+
"learning_rate": 0.001,
|
| 94 |
+
"loss": 1.8178,
|
| 95 |
+
"step": 26
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.95,
|
| 99 |
+
"learning_rate": 0.001,
|
| 100 |
+
"loss": 1.9188,
|
| 101 |
+
"step": 28
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.95,
|
| 105 |
+
"eval_loss": 1.694077968597412,
|
| 106 |
+
"eval_runtime": 84.303,
|
| 107 |
+
"eval_samples_per_second": 4.009,
|
| 108 |
+
"eval_steps_per_second": 0.51,
|
| 109 |
+
"step": 28
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.09,
|
| 113 |
+
"learning_rate": 0.001,
|
| 114 |
+
"loss": 1.6461,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.23,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"loss": 1.552,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.37,
|
| 125 |
+
"learning_rate": 0.001,
|
| 126 |
+
"loss": 1.4914,
|
| 127 |
+
"step": 34
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.5,
|
| 131 |
+
"learning_rate": 0.001,
|
| 132 |
+
"loss": 1.457,
|
| 133 |
+
"step": 36
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.64,
|
| 137 |
+
"learning_rate": 0.001,
|
| 138 |
+
"loss": 1.4499,
|
| 139 |
+
"step": 38
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.78,
|
| 143 |
+
"learning_rate": 0.001,
|
| 144 |
+
"loss": 1.4868,
|
| 145 |
+
"step": 40
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.92,
|
| 149 |
+
"learning_rate": 0.001,
|
| 150 |
+
"loss": 1.4297,
|
| 151 |
+
"step": 42
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.99,
|
| 155 |
+
"eval_loss": 1.5011385679244995,
|
| 156 |
+
"eval_runtime": 84.2558,
|
| 157 |
+
"eval_samples_per_second": 4.012,
|
| 158 |
+
"eval_steps_per_second": 0.51,
|
| 159 |
+
"step": 43
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.06,
|
| 163 |
+
"learning_rate": 0.001,
|
| 164 |
+
"loss": 1.3757,
|
| 165 |
+
"step": 44
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.2,
|
| 169 |
+
"learning_rate": 0.001,
|
| 170 |
+
"loss": 1.2701,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.34,
|
| 175 |
+
"learning_rate": 0.001,
|
| 176 |
+
"loss": 1.2826,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.48,
|
| 181 |
+
"learning_rate": 0.001,
|
| 182 |
+
"loss": 1.2945,
|
| 183 |
+
"step": 50
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.62,
|
| 187 |
+
"learning_rate": 0.001,
|
| 188 |
+
"loss": 1.2963,
|
| 189 |
+
"step": 52
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.76,
|
| 193 |
+
"learning_rate": 0.001,
|
| 194 |
+
"loss": 1.2933,
|
| 195 |
+
"step": 54
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.9,
|
| 199 |
+
"learning_rate": 0.001,
|
| 200 |
+
"loss": 1.2759,
|
| 201 |
+
"step": 56
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.97,
|
| 205 |
+
"eval_loss": 1.5048083066940308,
|
| 206 |
+
"eval_runtime": 84.2663,
|
| 207 |
+
"eval_samples_per_second": 4.011,
|
| 208 |
+
"eval_steps_per_second": 0.51,
|
| 209 |
+
"step": 57
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.03,
|
| 213 |
+
"learning_rate": 0.001,
|
| 214 |
+
"loss": 1.2446,
|
| 215 |
+
"step": 58
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.17,
|
| 219 |
+
"learning_rate": 0.001,
|
| 220 |
+
"loss": 1.0992,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.31,
|
| 225 |
+
"learning_rate": 0.001,
|
| 226 |
+
"loss": 1.0771,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.45,
|
| 231 |
+
"learning_rate": 0.001,
|
| 232 |
+
"loss": 1.1254,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 4.59,
|
| 237 |
+
"learning_rate": 0.001,
|
| 238 |
+
"loss": 1.1644,
|
| 239 |
+
"step": 66
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.73,
|
| 243 |
+
"learning_rate": 0.001,
|
| 244 |
+
"loss": 1.1485,
|
| 245 |
+
"step": 68
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 4.87,
|
| 249 |
+
"learning_rate": 0.001,
|
| 250 |
+
"loss": 1.1421,
|
| 251 |
+
"step": 70
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 4.94,
|
| 255 |
+
"eval_loss": 1.5463248491287231,
|
| 256 |
+
"eval_runtime": 84.2507,
|
| 257 |
+
"eval_samples_per_second": 4.012,
|
| 258 |
+
"eval_steps_per_second": 0.51,
|
| 259 |
+
"step": 71
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.01,
|
| 263 |
+
"learning_rate": 0.001,
|
| 264 |
+
"loss": 1.1233,
|
| 265 |
+
"step": 72
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 5.15,
|
| 269 |
+
"learning_rate": 0.001,
|
| 270 |
+
"loss": 0.8919,
|
| 271 |
+
"step": 74
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.29,
|
| 275 |
+
"learning_rate": 0.001,
|
| 276 |
+
"loss": 0.9349,
|
| 277 |
+
"step": 76
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 5.43,
|
| 281 |
+
"learning_rate": 0.001,
|
| 282 |
+
"loss": 0.9363,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.57,
|
| 287 |
+
"learning_rate": 0.001,
|
| 288 |
+
"loss": 0.9203,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.7,
|
| 293 |
+
"learning_rate": 0.001,
|
| 294 |
+
"loss": 0.9429,
|
| 295 |
+
"step": 82
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.84,
|
| 299 |
+
"learning_rate": 0.001,
|
| 300 |
+
"loss": 0.9495,
|
| 301 |
+
"step": 84
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.98,
|
| 305 |
+
"learning_rate": 0.001,
|
| 306 |
+
"loss": 0.9605,
|
| 307 |
+
"step": 86
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.98,
|
| 311 |
+
"eval_loss": 1.6269720792770386,
|
| 312 |
+
"eval_runtime": 84.2452,
|
| 313 |
+
"eval_samples_per_second": 4.012,
|
| 314 |
+
"eval_steps_per_second": 0.51,
|
| 315 |
+
"step": 86
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.12,
|
| 319 |
+
"learning_rate": 0.001,
|
| 320 |
+
"loss": 0.7747,
|
| 321 |
+
"step": 88
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.26,
|
| 325 |
+
"learning_rate": 0.001,
|
| 326 |
+
"loss": 0.7664,
|
| 327 |
+
"step": 90
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.4,
|
| 331 |
+
"learning_rate": 0.001,
|
| 332 |
+
"loss": 0.7998,
|
| 333 |
+
"step": 92
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.54,
|
| 337 |
+
"learning_rate": 0.001,
|
| 338 |
+
"loss": 0.7715,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.68,
|
| 343 |
+
"learning_rate": 0.001,
|
| 344 |
+
"loss": 0.8038,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 6.82,
|
| 349 |
+
"learning_rate": 0.001,
|
| 350 |
+
"loss": 0.8059,
|
| 351 |
+
"step": 98
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.96,
|
| 355 |
+
"learning_rate": 0.001,
|
| 356 |
+
"loss": 0.8082,
|
| 357 |
+
"step": 100
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 6.96,
|
| 361 |
+
"eval_loss": 1.7645633220672607,
|
| 362 |
+
"eval_runtime": 84.2691,
|
| 363 |
+
"eval_samples_per_second": 4.011,
|
| 364 |
+
"eval_steps_per_second": 0.51,
|
| 365 |
+
"step": 100
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.1,
|
| 369 |
+
"learning_rate": 0.001,
|
| 370 |
+
"loss": 0.6708,
|
| 371 |
+
"step": 102
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 7.23,
|
| 375 |
+
"learning_rate": 0.001,
|
| 376 |
+
"loss": 0.6186,
|
| 377 |
+
"step": 104
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 7.37,
|
| 381 |
+
"learning_rate": 0.001,
|
| 382 |
+
"loss": 0.6101,
|
| 383 |
+
"step": 106
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 7.51,
|
| 387 |
+
"learning_rate": 0.001,
|
| 388 |
+
"loss": 0.6328,
|
| 389 |
+
"step": 108
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.65,
|
| 393 |
+
"learning_rate": 0.001,
|
| 394 |
+
"loss": 0.6529,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.79,
|
| 399 |
+
"learning_rate": 0.001,
|
| 400 |
+
"loss": 0.6312,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.93,
|
| 405 |
+
"learning_rate": 0.001,
|
| 406 |
+
"loss": 0.664,
|
| 407 |
+
"step": 114
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 8.0,
|
| 411 |
+
"eval_loss": 1.78783118724823,
|
| 412 |
+
"eval_runtime": 84.2285,
|
| 413 |
+
"eval_samples_per_second": 4.013,
|
| 414 |
+
"eval_steps_per_second": 0.511,
|
| 415 |
+
"step": 115
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 8.07,
|
| 419 |
+
"learning_rate": 0.001,
|
| 420 |
+
"loss": 0.6177,
|
| 421 |
+
"step": 116
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 8.21,
|
| 425 |
+
"learning_rate": 0.001,
|
| 426 |
+
"loss": 0.5241,
|
| 427 |
+
"step": 118
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 8.35,
|
| 431 |
+
"learning_rate": 0.001,
|
| 432 |
+
"loss": 0.5173,
|
| 433 |
+
"step": 120
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 8.49,
|
| 437 |
+
"learning_rate": 0.001,
|
| 438 |
+
"loss": 0.5241,
|
| 439 |
+
"step": 122
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 8.63,
|
| 443 |
+
"learning_rate": 0.001,
|
| 444 |
+
"loss": 0.5546,
|
| 445 |
+
"step": 124
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 8.77,
|
| 449 |
+
"learning_rate": 0.001,
|
| 450 |
+
"loss": 0.5401,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 8.9,
|
| 455 |
+
"learning_rate": 0.001,
|
| 456 |
+
"loss": 0.5471,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 8.97,
|
| 461 |
+
"eval_loss": 1.9499958753585815,
|
| 462 |
+
"eval_runtime": 84.3243,
|
| 463 |
+
"eval_samples_per_second": 4.008,
|
| 464 |
+
"eval_steps_per_second": 0.51,
|
| 465 |
+
"step": 129
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.04,
|
| 469 |
+
"learning_rate": 0.001,
|
| 470 |
+
"loss": 0.526,
|
| 471 |
+
"step": 130
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.18,
|
| 475 |
+
"learning_rate": 0.001,
|
| 476 |
+
"loss": 0.409,
|
| 477 |
+
"step": 132
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.32,
|
| 481 |
+
"learning_rate": 0.001,
|
| 482 |
+
"loss": 0.4163,
|
| 483 |
+
"step": 134
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.46,
|
| 487 |
+
"learning_rate": 0.001,
|
| 488 |
+
"loss": 0.4304,
|
| 489 |
+
"step": 136
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 9.6,
|
| 493 |
+
"learning_rate": 0.001,
|
| 494 |
+
"loss": 0.4512,
|
| 495 |
+
"step": 138
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 9.74,
|
| 499 |
+
"learning_rate": 0.001,
|
| 500 |
+
"loss": 0.4396,
|
| 501 |
+
"step": 140
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.88,
|
| 505 |
+
"learning_rate": 0.001,
|
| 506 |
+
"loss": 0.4349,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 9.95,
|
| 511 |
+
"eval_loss": 1.9656596183776855,
|
| 512 |
+
"eval_runtime": 84.2136,
|
| 513 |
+
"eval_samples_per_second": 4.014,
|
| 514 |
+
"eval_steps_per_second": 0.511,
|
| 515 |
+
"step": 143
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 10.02,
|
| 519 |
+
"learning_rate": 0.001,
|
| 520 |
+
"loss": 0.4077,
|
| 521 |
+
"step": 144
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 10.16,
|
| 525 |
+
"learning_rate": 0.001,
|
| 526 |
+
"loss": 0.3439,
|
| 527 |
+
"step": 146
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 10.3,
|
| 531 |
+
"learning_rate": 0.001,
|
| 532 |
+
"loss": 0.3503,
|
| 533 |
+
"step": 148
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 10.43,
|
| 537 |
+
"learning_rate": 0.001,
|
| 538 |
+
"loss": 0.3572,
|
| 539 |
+
"step": 150
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 10.57,
|
| 543 |
+
"learning_rate": 0.001,
|
| 544 |
+
"loss": 0.3643,
|
| 545 |
+
"step": 152
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 10.71,
|
| 549 |
+
"learning_rate": 0.001,
|
| 550 |
+
"loss": 0.3516,
|
| 551 |
+
"step": 154
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 10.85,
|
| 555 |
+
"learning_rate": 0.001,
|
| 556 |
+
"loss": 0.377,
|
| 557 |
+
"step": 156
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 10.99,
|
| 561 |
+
"learning_rate": 0.001,
|
| 562 |
+
"loss": 0.4338,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 10.99,
|
| 567 |
+
"eval_loss": 2.135113477706909,
|
| 568 |
+
"eval_runtime": 84.161,
|
| 569 |
+
"eval_samples_per_second": 4.016,
|
| 570 |
+
"eval_steps_per_second": 0.511,
|
| 571 |
+
"step": 158
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 11.13,
|
| 575 |
+
"learning_rate": 0.001,
|
| 576 |
+
"loss": 0.2715,
|
| 577 |
+
"step": 160
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 11.27,
|
| 581 |
+
"learning_rate": 0.001,
|
| 582 |
+
"loss": 0.2391,
|
| 583 |
+
"step": 162
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 11.41,
|
| 587 |
+
"learning_rate": 0.001,
|
| 588 |
+
"loss": 0.2958,
|
| 589 |
+
"step": 164
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 11.55,
|
| 593 |
+
"learning_rate": 0.001,
|
| 594 |
+
"loss": 0.3101,
|
| 595 |
+
"step": 166
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 11.69,
|
| 599 |
+
"learning_rate": 0.001,
|
| 600 |
+
"loss": 0.3417,
|
| 601 |
+
"step": 168
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 11.83,
|
| 605 |
+
"learning_rate": 0.001,
|
| 606 |
+
"loss": 0.3292,
|
| 607 |
+
"step": 170
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 11.97,
|
| 611 |
+
"learning_rate": 0.001,
|
| 612 |
+
"loss": 0.2887,
|
| 613 |
+
"step": 172
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 11.97,
|
| 617 |
+
"eval_loss": 2.11661434173584,
|
| 618 |
+
"eval_runtime": 84.1912,
|
| 619 |
+
"eval_samples_per_second": 4.015,
|
| 620 |
+
"eval_steps_per_second": 0.511,
|
| 621 |
+
"step": 172
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.1,
|
| 625 |
+
"learning_rate": 0.001,
|
| 626 |
+
"loss": 0.2532,
|
| 627 |
+
"step": 174
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 12.24,
|
| 631 |
+
"learning_rate": 0.001,
|
| 632 |
+
"loss": 0.2565,
|
| 633 |
+
"step": 176
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 12.38,
|
| 637 |
+
"learning_rate": 0.001,
|
| 638 |
+
"loss": 0.2791,
|
| 639 |
+
"step": 178
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.52,
|
| 643 |
+
"learning_rate": 0.001,
|
| 644 |
+
"loss": 0.2803,
|
| 645 |
+
"step": 180
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 12.66,
|
| 649 |
+
"learning_rate": 0.001,
|
| 650 |
+
"loss": 0.3015,
|
| 651 |
+
"step": 182
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 12.8,
|
| 655 |
+
"learning_rate": 0.001,
|
| 656 |
+
"loss": 0.2764,
|
| 657 |
+
"step": 184
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 12.94,
|
| 661 |
+
"learning_rate": 0.001,
|
| 662 |
+
"loss": 0.2753,
|
| 663 |
+
"step": 186
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 12.94,
|
| 667 |
+
"eval_loss": 2.4357352256774902,
|
| 668 |
+
"eval_runtime": 84.1848,
|
| 669 |
+
"eval_samples_per_second": 4.015,
|
| 670 |
+
"eval_steps_per_second": 0.511,
|
| 671 |
+
"step": 186
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 13.08,
|
| 675 |
+
"learning_rate": 0.001,
|
| 676 |
+
"loss": 0.2563,
|
| 677 |
+
"step": 188
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 13.22,
|
| 681 |
+
"learning_rate": 0.001,
|
| 682 |
+
"loss": 0.2024,
|
| 683 |
+
"step": 190
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 13.36,
|
| 687 |
+
"learning_rate": 0.001,
|
| 688 |
+
"loss": 0.2252,
|
| 689 |
+
"step": 192
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 13.5,
|
| 693 |
+
"learning_rate": 0.001,
|
| 694 |
+
"loss": 0.2487,
|
| 695 |
+
"step": 194
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 13.63,
|
| 699 |
+
"learning_rate": 0.001,
|
| 700 |
+
"loss": 0.2086,
|
| 701 |
+
"step": 196
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 13.77,
|
| 705 |
+
"learning_rate": 0.001,
|
| 706 |
+
"loss": 0.2181,
|
| 707 |
+
"step": 198
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 13.91,
|
| 711 |
+
"learning_rate": 0.001,
|
| 712 |
+
"loss": 0.2114,
|
| 713 |
+
"step": 200
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 13.98,
|
| 717 |
+
"eval_loss": 2.5789217948913574,
|
| 718 |
+
"eval_runtime": 84.14,
|
| 719 |
+
"eval_samples_per_second": 4.017,
|
| 720 |
+
"eval_steps_per_second": 0.511,
|
| 721 |
+
"step": 201
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 14.05,
|
| 725 |
+
"learning_rate": 0.001,
|
| 726 |
+
"loss": 0.1828,
|
| 727 |
+
"step": 202
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 14.19,
|
| 731 |
+
"learning_rate": 0.001,
|
| 732 |
+
"loss": 0.2025,
|
| 733 |
+
"step": 204
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 14.33,
|
| 737 |
+
"learning_rate": 0.001,
|
| 738 |
+
"loss": 0.1991,
|
| 739 |
+
"step": 206
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 14.47,
|
| 743 |
+
"learning_rate": 0.001,
|
| 744 |
+
"loss": 0.1844,
|
| 745 |
+
"step": 208
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 14.61,
|
| 749 |
+
"learning_rate": 0.001,
|
| 750 |
+
"loss": 0.1934,
|
| 751 |
+
"step": 210
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 14.75,
|
| 755 |
+
"learning_rate": 0.001,
|
| 756 |
+
"loss": 0.2,
|
| 757 |
+
"step": 212
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 14.89,
|
| 761 |
+
"learning_rate": 0.001,
|
| 762 |
+
"loss": 0.1805,
|
| 763 |
+
"step": 214
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 14.96,
|
| 767 |
+
"eval_loss": 2.6075170040130615,
|
| 768 |
+
"eval_runtime": 84.2554,
|
| 769 |
+
"eval_samples_per_second": 4.012,
|
| 770 |
+
"eval_steps_per_second": 0.51,
|
| 771 |
+
"step": 215
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 15.03,
|
| 775 |
+
"learning_rate": 0.001,
|
| 776 |
+
"loss": 0.1739,
|
| 777 |
+
"step": 216
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 15.17,
|
| 781 |
+
"learning_rate": 0.001,
|
| 782 |
+
"loss": 0.1504,
|
| 783 |
+
"step": 218
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 15.3,
|
| 787 |
+
"learning_rate": 0.001,
|
| 788 |
+
"loss": 0.1431,
|
| 789 |
+
"step": 220
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 15.44,
|
| 793 |
+
"learning_rate": 0.001,
|
| 794 |
+
"loss": 0.152,
|
| 795 |
+
"step": 222
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 15.58,
|
| 799 |
+
"learning_rate": 0.001,
|
| 800 |
+
"loss": 0.142,
|
| 801 |
+
"step": 224
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 15.72,
|
| 805 |
+
"learning_rate": 0.001,
|
| 806 |
+
"loss": 0.145,
|
| 807 |
+
"step": 226
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 15.86,
|
| 811 |
+
"learning_rate": 0.001,
|
| 812 |
+
"loss": 0.1476,
|
| 813 |
+
"step": 228
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 16.0,
|
| 817 |
+
"learning_rate": 0.001,
|
| 818 |
+
"loss": 0.1543,
|
| 819 |
+
"step": 230
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 16.0,
|
| 823 |
+
"eval_loss": 2.5597331523895264,
|
| 824 |
+
"eval_runtime": 84.1535,
|
| 825 |
+
"eval_samples_per_second": 4.016,
|
| 826 |
+
"eval_steps_per_second": 0.511,
|
| 827 |
+
"step": 230
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 16.14,
|
| 831 |
+
"learning_rate": 0.001,
|
| 832 |
+
"loss": 0.1245,
|
| 833 |
+
"step": 232
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 16.28,
|
| 837 |
+
"learning_rate": 0.001,
|
| 838 |
+
"loss": 0.1204,
|
| 839 |
+
"step": 234
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 16.42,
|
| 843 |
+
"learning_rate": 0.001,
|
| 844 |
+
"loss": 0.2117,
|
| 845 |
+
"step": 236
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 16.56,
|
| 849 |
+
"learning_rate": 0.001,
|
| 850 |
+
"loss": 0.6894,
|
| 851 |
+
"step": 238
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 16.7,
|
| 855 |
+
"learning_rate": 0.001,
|
| 856 |
+
"loss": 0.35,
|
| 857 |
+
"step": 240
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 16.83,
|
| 861 |
+
"learning_rate": 0.001,
|
| 862 |
+
"loss": 0.8395,
|
| 863 |
+
"step": 242
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 16.97,
|
| 867 |
+
"learning_rate": 0.001,
|
| 868 |
+
"loss": 0.5166,
|
| 869 |
+
"step": 244
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 16.97,
|
| 873 |
+
"eval_loss": 2.5066745281219482,
|
| 874 |
+
"eval_runtime": 84.1866,
|
| 875 |
+
"eval_samples_per_second": 4.015,
|
| 876 |
+
"eval_steps_per_second": 0.511,
|
| 877 |
+
"step": 244
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 17.11,
|
| 881 |
+
"learning_rate": 0.001,
|
| 882 |
+
"loss": 0.202,
|
| 883 |
+
"step": 246
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 17.25,
|
| 887 |
+
"learning_rate": 0.001,
|
| 888 |
+
"loss": 0.1247,
|
| 889 |
+
"step": 248
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 17.39,
|
| 893 |
+
"learning_rate": 0.001,
|
| 894 |
+
"loss": 0.1368,
|
| 895 |
+
"step": 250
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 17.53,
|
| 899 |
+
"learning_rate": 0.001,
|
| 900 |
+
"loss": 0.1096,
|
| 901 |
+
"step": 252
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 17.67,
|
| 905 |
+
"learning_rate": 0.001,
|
| 906 |
+
"loss": 0.1066,
|
| 907 |
+
"step": 254
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 17.81,
|
| 911 |
+
"learning_rate": 0.001,
|
| 912 |
+
"loss": 0.1078,
|
| 913 |
+
"step": 256
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 17.95,
|
| 917 |
+
"learning_rate": 0.001,
|
| 918 |
+
"loss": 0.1117,
|
| 919 |
+
"step": 258
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 17.95,
|
| 923 |
+
"eval_loss": 2.808701515197754,
|
| 924 |
+
"eval_runtime": 84.1837,
|
| 925 |
+
"eval_samples_per_second": 4.015,
|
| 926 |
+
"eval_steps_per_second": 0.511,
|
| 927 |
+
"step": 258
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 18.09,
|
| 931 |
+
"learning_rate": 0.001,
|
| 932 |
+
"loss": 0.0934,
|
| 933 |
+
"step": 260
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 18.23,
|
| 937 |
+
"learning_rate": 0.001,
|
| 938 |
+
"loss": 0.0793,
|
| 939 |
+
"step": 262
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 18.37,
|
| 943 |
+
"learning_rate": 0.001,
|
| 944 |
+
"loss": 0.0887,
|
| 945 |
+
"step": 264
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 18.5,
|
| 949 |
+
"learning_rate": 0.001,
|
| 950 |
+
"loss": 0.103,
|
| 951 |
+
"step": 266
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 18.64,
|
| 955 |
+
"learning_rate": 0.001,
|
| 956 |
+
"loss": 0.0847,
|
| 957 |
+
"step": 268
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 18.78,
|
| 961 |
+
"learning_rate": 0.001,
|
| 962 |
+
"loss": 0.0869,
|
| 963 |
+
"step": 270
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 18.92,
|
| 967 |
+
"learning_rate": 0.001,
|
| 968 |
+
"loss": 0.0895,
|
| 969 |
+
"step": 272
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 18.99,
|
| 973 |
+
"eval_loss": 2.7578108310699463,
|
| 974 |
+
"eval_runtime": 84.2046,
|
| 975 |
+
"eval_samples_per_second": 4.014,
|
| 976 |
+
"eval_steps_per_second": 0.511,
|
| 977 |
+
"step": 273
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 19.06,
|
| 981 |
+
"learning_rate": 0.001,
|
| 982 |
+
"loss": 0.0884,
|
| 983 |
+
"step": 274
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 19.2,
|
| 987 |
+
"learning_rate": 0.001,
|
| 988 |
+
"loss": 0.0838,
|
| 989 |
+
"step": 276
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 19.34,
|
| 993 |
+
"learning_rate": 0.001,
|
| 994 |
+
"loss": 0.0731,
|
| 995 |
+
"step": 278
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 19.48,
|
| 999 |
+
"learning_rate": 0.001,
|
| 1000 |
+
"loss": 0.0779,
|
| 1001 |
+
"step": 280
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 19.48,
|
| 1005 |
+
"eval_loss": 2.892078161239624,
|
| 1006 |
+
"eval_runtime": 84.2063,
|
| 1007 |
+
"eval_samples_per_second": 4.014,
|
| 1008 |
+
"eval_steps_per_second": 0.511,
|
| 1009 |
+
"step": 280
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 19.48,
|
| 1013 |
+
"step": 280,
|
| 1014 |
+
"total_flos": 4.895224157149471e+18,
|
| 1015 |
+
"train_loss": 0.722327525381531,
|
| 1016 |
+
"train_runtime": 70402.3599,
|
| 1017 |
+
"train_samples_per_second": 1.043,
|
| 1018 |
+
"train_steps_per_second": 0.004
|
| 1019 |
+
}
|
| 1020 |
+
],
|
| 1021 |
+
"logging_steps": 2,
|
| 1022 |
+
"max_steps": 280,
|
| 1023 |
+
"num_input_tokens_seen": 0,
|
| 1024 |
+
"num_train_epochs": 20,
|
| 1025 |
+
"save_steps": 500,
|
| 1026 |
+
"total_flos": 4.895224157149471e+18,
|
| 1027 |
+
"train_batch_size": 8,
|
| 1028 |
+
"trial_name": null,
|
| 1029 |
+
"trial_params": null
|
| 1030 |
+
}
|