Training in progress, epoch 1, checkpoint
Browse files- last-checkpoint/config.json +62 -0
- last-checkpoint/generation_config.json +6 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +56 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"task_specific_params": {
|
29 |
+
"summarization": {
|
30 |
+
"early_stopping": true,
|
31 |
+
"length_penalty": 2.0,
|
32 |
+
"max_length": 200,
|
33 |
+
"min_length": 30,
|
34 |
+
"no_repeat_ngram_size": 3,
|
35 |
+
"num_beams": 4,
|
36 |
+
"prefix": "summarize: "
|
37 |
+
},
|
38 |
+
"translation_en_to_de": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"max_length": 300,
|
41 |
+
"num_beams": 4,
|
42 |
+
"prefix": "translate English to German: "
|
43 |
+
},
|
44 |
+
"translation_en_to_fr": {
|
45 |
+
"early_stopping": true,
|
46 |
+
"max_length": 300,
|
47 |
+
"num_beams": 4,
|
48 |
+
"prefix": "translate English to French: "
|
49 |
+
},
|
50 |
+
"translation_en_to_ro": {
|
51 |
+
"early_stopping": true,
|
52 |
+
"max_length": 300,
|
53 |
+
"num_beams": 4,
|
54 |
+
"prefix": "translate English to Romanian: "
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"tie_word_embeddings": false,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.34.1",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 32128
|
62 |
+
}
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.34.1"
|
6 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5771d626f5f76c2b40ece2e4df39b8bd24efbe70d36c0311ddd3dd81b57e21c1
|
3 |
+
size 2371770
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b636a897f64e4794cb84771a349ebd9bde27930ac81d66a20be31aef9dc7faeb
|
3 |
+
size 990409330
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cea44ad93fec8c4df820561aaed097d102f17e9be600b9a116f68fe9875b8e4
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4afbee4eef31ae6f0f2f4373f90e6cf49579bddfce99e5131fce75c63b548f86
|
3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.409773349761963,
|
3 |
+
"best_model_checkpoint": "dq158/pingusPongus/checkpoint-1581",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1581,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.32,
|
13 |
+
"learning_rate": 0.0001,
|
14 |
+
"loss": 3.1034,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.63,
|
19 |
+
"learning_rate": 9.993631921956987e-05,
|
20 |
+
"loss": 2.6893,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.95,
|
25 |
+
"learning_rate": 9.974543908795133e-05,
|
26 |
+
"loss": 2.5782,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.0,
|
31 |
+
"eval_bleu": 1.0,
|
32 |
+
"eval_brevity_penalty": 1.0,
|
33 |
+
"eval_length_ratio": 1.0,
|
34 |
+
"eval_loss": 2.409773349761963,
|
35 |
+
"eval_precisions": [
|
36 |
+
1.0,
|
37 |
+
1.0,
|
38 |
+
1.0,
|
39 |
+
1.0
|
40 |
+
],
|
41 |
+
"eval_reference_length": 52663,
|
42 |
+
"eval_runtime": 589.2444,
|
43 |
+
"eval_samples_per_second": 4.771,
|
44 |
+
"eval_steps_per_second": 0.597,
|
45 |
+
"eval_translation_length": 52663,
|
46 |
+
"step": 1581
|
47 |
+
}
|
48 |
+
],
|
49 |
+
"logging_steps": 500,
|
50 |
+
"max_steps": 31620,
|
51 |
+
"num_train_epochs": 20,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 1.7318198200762368e+16,
|
54 |
+
"trial_name": null,
|
55 |
+
"trial_params": null
|
56 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb48fdc1c4d2c2b6968feccddbbe4b6b4a3bd9d40b837b61c648facfca890857
|
3 |
+
size 4664
|