Vincent Marklynn
commited on
Commit
•
c2a9b51
1
Parent(s):
f151f60
moved checkpoint-40 to working dir
Browse files- generation_config.json +16 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +42 -0
- training_args.bin +3 -0
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"length_penalty": 2.0,
|
| 10 |
+
"max_length": 142,
|
| 11 |
+
"min_length": 56,
|
| 12 |
+
"no_repeat_ngram_size": 3,
|
| 13 |
+
"num_beams": 4,
|
| 14 |
+
"pad_token_id": 1,
|
| 15 |
+
"transformers_version": "4.26.0"
|
| 16 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ab8639119c1b8569dda18bf98ce0b7b3d8371bf3a909d27132ee761df310ee3
|
| 3 |
+
size 3250609115
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:062a01b0385214a4b30120e4f5d9aea8075ca9dbb55344ab6b9d8e76ce9a85da
|
| 3 |
+
size 1625530125
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2482b2cc11a386c3e0e0cc8802f1bb0a9c34f292d4e4acc11ae70f117bb1ae7
|
| 3 |
+
size 13553
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51cb491e0c1dd48d27b2af6be60fff4e0d3d16435dbf3bb4f48a394c2730266e
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.1361048221588135,
|
| 3 |
+
"best_model_checkpoint": "bart-large-cnn-samsum-acsi-ami/checkpoint-40",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 40,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_gen_len": 108.5,
|
| 13 |
+
"eval_loss": 3.2094905376434326,
|
| 14 |
+
"eval_rouge1": 39.8174,
|
| 15 |
+
"eval_rouge2": 11.5559,
|
| 16 |
+
"eval_rougeL": 24.0296,
|
| 17 |
+
"eval_rougeLsum": 36.3048,
|
| 18 |
+
"eval_runtime": 212.8556,
|
| 19 |
+
"eval_samples_per_second": 0.188,
|
| 20 |
+
"eval_steps_per_second": 0.023,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_gen_len": 108.15,
|
| 26 |
+
"eval_loss": 3.1361048221588135,
|
| 27 |
+
"eval_rouge1": 39.7563,
|
| 28 |
+
"eval_rouge2": 11.1286,
|
| 29 |
+
"eval_rougeL": 23.2632,
|
| 30 |
+
"eval_rougeLsum": 36.5664,
|
| 31 |
+
"eval_runtime": 209.462,
|
| 32 |
+
"eval_samples_per_second": 0.191,
|
| 33 |
+
"eval_steps_per_second": 0.024,
|
| 34 |
+
"step": 40
|
| 35 |
+
}
|
| 36 |
+
],
|
| 37 |
+
"max_steps": 100,
|
| 38 |
+
"num_train_epochs": 5,
|
| 39 |
+
"total_flos": 676136635858944.0,
|
| 40 |
+
"trial_name": null,
|
| 41 |
+
"trial_params": null
|
| 42 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d16d4bbe3c1a3a528679fd7f699ed3222c17ad7a61017d9a075780b14236299a
|
| 3 |
+
size 3643
|