Upload folder using huggingface_hub
Browse files- checkpoint-1000/config.json +73 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +63 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1455/config.json +73 -0
- checkpoint-1455/model.safetensors +3 -0
- checkpoint-1455/optimizer.pt +3 -0
- checkpoint-1455/rng_state.pth +3 -0
- checkpoint-1455/scheduler.pt +3 -0
- checkpoint-1455/trainer_state.json +63 -0
- checkpoint-1455/training_args.bin +3 -0
- checkpoint-500/config.json +73 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +48 -0
- checkpoint-500/training_args.bin +3 -0
- config.json +73 -0
- model.safetensors +3 -0
- runs/Dec27_05-33-36_debian/events.out.tfevents.1735277618.debian.3575638.0 +3 -0
- runs/Dec27_05-35-26_debian/events.out.tfevents.1735277727.debian.3577983.0 +3 -0
- runs/Dec27_05-36-37_debian/events.out.tfevents.1735277798.debian.3579469.0 +3 -0
- runs/Dec27_05-52-31_debian/events.out.tfevents.1735278751.debian.3602307.0 +3 -0
- runs/Dec27_06-07-26_debian/events.out.tfevents.1735279646.debian.3622194.0 +3 -0
- training_args.bin +3 -0
checkpoint-1000/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForSequenceClassification"
|
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 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2"
|
19 |
+
},
|
20 |
+
"initializer_factor": 1.0,
|
21 |
+
"is_encoder_decoder": true,
|
22 |
+
"is_gated_act": true,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2
|
27 |
+
},
|
28 |
+
"layer_norm_epsilon": 1e-06,
|
29 |
+
"model_type": "t5",
|
30 |
+
"n_positions": 512,
|
31 |
+
"num_decoder_layers": 12,
|
32 |
+
"num_heads": 12,
|
33 |
+
"num_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"relative_attention_max_distance": 128,
|
38 |
+
"relative_attention_num_buckets": 32,
|
39 |
+
"task_specific_params": {
|
40 |
+
"summarization": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"length_penalty": 2.0,
|
43 |
+
"max_length": 200,
|
44 |
+
"min_length": 30,
|
45 |
+
"no_repeat_ngram_size": 3,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "summarize: "
|
48 |
+
},
|
49 |
+
"translation_en_to_de": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to German: "
|
54 |
+
},
|
55 |
+
"translation_en_to_fr": {
|
56 |
+
"early_stopping": true,
|
57 |
+
"max_length": 300,
|
58 |
+
"num_beams": 4,
|
59 |
+
"prefix": "translate English to French: "
|
60 |
+
},
|
61 |
+
"translation_en_to_ro": {
|
62 |
+
"early_stopping": true,
|
63 |
+
"max_length": 300,
|
64 |
+
"num_beams": 4,
|
65 |
+
"prefix": "translate English to Romanian: "
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"tie_word_embeddings": false,
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.47.1",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 32128
|
73 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d4481ed556f06a1e4ac80f48ae5be58bd971566e0d3ce9a885043429f597224
|
3 |
+
size 894023124
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6c18e4f98c85f02ab9678bc8d0a4bb4a22516882ada79ba6e7e440e726efa2b
|
3 |
+
size 1788211642
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b756a7436bd25e612eba97582f5cc5fbb7dba1c491729db3223cb2d1af1df64
|
3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff97c58a527005d014241becb33315d6e6813095a4a6af2a05d1b7b43964faa4
|
3 |
+
size 1064
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0618556701030926,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.42261144518852234,
|
14 |
+
"eval_runtime": 6.9522,
|
15 |
+
"eval_samples_per_second": 139.523,
|
16 |
+
"eval_steps_per_second": 17.548,
|
17 |
+
"step": 485
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.0309278350515463,
|
21 |
+
"grad_norm": 2.8641510009765625,
|
22 |
+
"learning_rate": 1.3127147766323025e-05,
|
23 |
+
"loss": 0.6796,
|
24 |
+
"step": 500
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_loss": 0.38285189867019653,
|
29 |
+
"eval_runtime": 6.8857,
|
30 |
+
"eval_samples_per_second": 140.871,
|
31 |
+
"eval_steps_per_second": 17.718,
|
32 |
+
"step": 970
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0618556701030926,
|
36 |
+
"grad_norm": 1.466252326965332,
|
37 |
+
"learning_rate": 6.254295532646049e-06,
|
38 |
+
"loss": 0.3931,
|
39 |
+
"step": 1000
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 1455,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"save_steps": 500,
|
47 |
+
"stateful_callbacks": {
|
48 |
+
"TrainerControl": {
|
49 |
+
"args": {
|
50 |
+
"should_epoch_stop": false,
|
51 |
+
"should_evaluate": false,
|
52 |
+
"should_log": false,
|
53 |
+
"should_save": true,
|
54 |
+
"should_training_stop": false
|
55 |
+
},
|
56 |
+
"attributes": {}
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"total_flos": 886651097220144.0,
|
60 |
+
"train_batch_size": 8,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0a4f56674f8158c153559cb00991d39e9e1da7258c61422695c423d072e36a2
|
3 |
+
size 5368
|
checkpoint-1455/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForSequenceClassification"
|
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 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2"
|
19 |
+
},
|
20 |
+
"initializer_factor": 1.0,
|
21 |
+
"is_encoder_decoder": true,
|
22 |
+
"is_gated_act": true,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2
|
27 |
+
},
|
28 |
+
"layer_norm_epsilon": 1e-06,
|
29 |
+
"model_type": "t5",
|
30 |
+
"n_positions": 512,
|
31 |
+
"num_decoder_layers": 12,
|
32 |
+
"num_heads": 12,
|
33 |
+
"num_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"relative_attention_max_distance": 128,
|
38 |
+
"relative_attention_num_buckets": 32,
|
39 |
+
"task_specific_params": {
|
40 |
+
"summarization": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"length_penalty": 2.0,
|
43 |
+
"max_length": 200,
|
44 |
+
"min_length": 30,
|
45 |
+
"no_repeat_ngram_size": 3,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "summarize: "
|
48 |
+
},
|
49 |
+
"translation_en_to_de": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to German: "
|
54 |
+
},
|
55 |
+
"translation_en_to_fr": {
|
56 |
+
"early_stopping": true,
|
57 |
+
"max_length": 300,
|
58 |
+
"num_beams": 4,
|
59 |
+
"prefix": "translate English to French: "
|
60 |
+
},
|
61 |
+
"translation_en_to_ro": {
|
62 |
+
"early_stopping": true,
|
63 |
+
"max_length": 300,
|
64 |
+
"num_beams": 4,
|
65 |
+
"prefix": "translate English to Romanian: "
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"tie_word_embeddings": false,
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.47.1",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 32128
|
73 |
+
}
|
checkpoint-1455/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2234af38ef801c0a87312e17ffcad5d716c14d6180b1e340ba9702198a0fd485
|
3 |
+
size 894023124
|
checkpoint-1455/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e4ea6a84c370363dc06c35ae7525f4931f238b8c1b20461c08795f33d5b7efb
|
3 |
+
size 1788211642
|
checkpoint-1455/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ad93379655ac469f427b91f7b54483b0039f995d02e80ba16e9c130c496a86e
|
3 |
+
size 14244
|
checkpoint-1455/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275af64cb0546358bc3d8f4d54e6474cd386fd63d6765ec65e18390a5f3dca00
|
3 |
+
size 1064
|
checkpoint-1455/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1455,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.42261144518852234,
|
14 |
+
"eval_runtime": 6.9522,
|
15 |
+
"eval_samples_per_second": 139.523,
|
16 |
+
"eval_steps_per_second": 17.548,
|
17 |
+
"step": 485
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.0309278350515463,
|
21 |
+
"grad_norm": 2.8641510009765625,
|
22 |
+
"learning_rate": 1.3127147766323025e-05,
|
23 |
+
"loss": 0.6796,
|
24 |
+
"step": 500
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_loss": 0.38285189867019653,
|
29 |
+
"eval_runtime": 6.8857,
|
30 |
+
"eval_samples_per_second": 140.871,
|
31 |
+
"eval_steps_per_second": 17.718,
|
32 |
+
"step": 970
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0618556701030926,
|
36 |
+
"grad_norm": 1.466252326965332,
|
37 |
+
"learning_rate": 6.254295532646049e-06,
|
38 |
+
"loss": 0.3931,
|
39 |
+
"step": 1000
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 1455,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"save_steps": 500,
|
47 |
+
"stateful_callbacks": {
|
48 |
+
"TrainerControl": {
|
49 |
+
"args": {
|
50 |
+
"should_epoch_stop": false,
|
51 |
+
"should_evaluate": false,
|
52 |
+
"should_log": false,
|
53 |
+
"should_save": true,
|
54 |
+
"should_training_stop": true
|
55 |
+
},
|
56 |
+
"attributes": {}
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"total_flos": 1290037407216696.0,
|
60 |
+
"train_batch_size": 8,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
checkpoint-1455/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0a4f56674f8158c153559cb00991d39e9e1da7258c61422695c423d072e36a2
|
3 |
+
size 5368
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForSequenceClassification"
|
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 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2"
|
19 |
+
},
|
20 |
+
"initializer_factor": 1.0,
|
21 |
+
"is_encoder_decoder": true,
|
22 |
+
"is_gated_act": true,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2
|
27 |
+
},
|
28 |
+
"layer_norm_epsilon": 1e-06,
|
29 |
+
"model_type": "t5",
|
30 |
+
"n_positions": 512,
|
31 |
+
"num_decoder_layers": 12,
|
32 |
+
"num_heads": 12,
|
33 |
+
"num_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"relative_attention_max_distance": 128,
|
38 |
+
"relative_attention_num_buckets": 32,
|
39 |
+
"task_specific_params": {
|
40 |
+
"summarization": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"length_penalty": 2.0,
|
43 |
+
"max_length": 200,
|
44 |
+
"min_length": 30,
|
45 |
+
"no_repeat_ngram_size": 3,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "summarize: "
|
48 |
+
},
|
49 |
+
"translation_en_to_de": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to German: "
|
54 |
+
},
|
55 |
+
"translation_en_to_fr": {
|
56 |
+
"early_stopping": true,
|
57 |
+
"max_length": 300,
|
58 |
+
"num_beams": 4,
|
59 |
+
"prefix": "translate English to French: "
|
60 |
+
},
|
61 |
+
"translation_en_to_ro": {
|
62 |
+
"early_stopping": true,
|
63 |
+
"max_length": 300,
|
64 |
+
"num_beams": 4,
|
65 |
+
"prefix": "translate English to Romanian: "
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"tie_word_embeddings": false,
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.47.1",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 32128
|
73 |
+
}
|
checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f789fb3a64bb3d3da5c05b694f6b85b477d7df94dfc430daccf0e346639a798e
|
3 |
+
size 894023124
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73b468103bbfc2060fa972425da1dc4e3abfc364989bbee8eb792eb29aeca506
|
3 |
+
size 1788211642
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63015f9c9da9c1eb68161ed45f5059e4d5e15a0f0c6e8e6c4440dbd2a86011ae
|
3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:467520a4a26a0774e35aff43925f1cec3b52f665aeb514f73a5e99d4ce275a2e
|
3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0309278350515463,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.42261144518852234,
|
14 |
+
"eval_runtime": 6.9522,
|
15 |
+
"eval_samples_per_second": 139.523,
|
16 |
+
"eval_steps_per_second": 17.548,
|
17 |
+
"step": 485
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.0309278350515463,
|
21 |
+
"grad_norm": 2.8641510009765625,
|
22 |
+
"learning_rate": 1.3127147766323025e-05,
|
23 |
+
"loss": 0.6796,
|
24 |
+
"step": 500
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 1455,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 3,
|
31 |
+
"save_steps": 500,
|
32 |
+
"stateful_callbacks": {
|
33 |
+
"TrainerControl": {
|
34 |
+
"args": {
|
35 |
+
"should_epoch_stop": false,
|
36 |
+
"should_evaluate": false,
|
37 |
+
"should_log": false,
|
38 |
+
"should_save": true,
|
39 |
+
"should_training_stop": false
|
40 |
+
},
|
41 |
+
"attributes": {}
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"total_flos": 443325548610072.0,
|
45 |
+
"train_batch_size": 8,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": null
|
48 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0a4f56674f8158c153559cb00991d39e9e1da7258c61422695c423d072e36a2
|
3 |
+
size 5368
|
config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForSequenceClassification"
|
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 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2"
|
19 |
+
},
|
20 |
+
"initializer_factor": 1.0,
|
21 |
+
"is_encoder_decoder": true,
|
22 |
+
"is_gated_act": true,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2
|
27 |
+
},
|
28 |
+
"layer_norm_epsilon": 1e-06,
|
29 |
+
"model_type": "t5",
|
30 |
+
"n_positions": 512,
|
31 |
+
"num_decoder_layers": 12,
|
32 |
+
"num_heads": 12,
|
33 |
+
"num_layers": 12,
|
34 |
+
"output_past": true,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"relative_attention_max_distance": 128,
|
38 |
+
"relative_attention_num_buckets": 32,
|
39 |
+
"task_specific_params": {
|
40 |
+
"summarization": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"length_penalty": 2.0,
|
43 |
+
"max_length": 200,
|
44 |
+
"min_length": 30,
|
45 |
+
"no_repeat_ngram_size": 3,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "summarize: "
|
48 |
+
},
|
49 |
+
"translation_en_to_de": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to German: "
|
54 |
+
},
|
55 |
+
"translation_en_to_fr": {
|
56 |
+
"early_stopping": true,
|
57 |
+
"max_length": 300,
|
58 |
+
"num_beams": 4,
|
59 |
+
"prefix": "translate English to French: "
|
60 |
+
},
|
61 |
+
"translation_en_to_ro": {
|
62 |
+
"early_stopping": true,
|
63 |
+
"max_length": 300,
|
64 |
+
"num_beams": 4,
|
65 |
+
"prefix": "translate English to Romanian: "
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"tie_word_embeddings": false,
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.47.1",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 32128
|
73 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2234af38ef801c0a87312e17ffcad5d716c14d6180b1e340ba9702198a0fd485
|
3 |
+
size 894023124
|
runs/Dec27_05-33-36_debian/events.out.tfevents.1735277618.debian.3575638.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be9f902917d6def40e1e02f68f536273ad9e85e278da529d81001a3cb68e8d5e
|
3 |
+
size 4184
|
runs/Dec27_05-35-26_debian/events.out.tfevents.1735277727.debian.3577983.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b301a69e50f918cc291259cfcf83c050fc314b8ffaf55675c0cf6e8c5aa9547
|
3 |
+
size 4184
|
runs/Dec27_05-36-37_debian/events.out.tfevents.1735277798.debian.3579469.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea9fea4c34d9516d78b5ac169e3c3048cd3f2588ca5525d3fc7c1ec6594aef68
|
3 |
+
size 7707
|
runs/Dec27_05-52-31_debian/events.out.tfevents.1735278751.debian.3602307.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3d64438bec602bcb5363f5aadbebfa8c2f8c4903dc40227e9ad541013126541
|
3 |
+
size 7707
|
runs/Dec27_06-07-26_debian/events.out.tfevents.1735279646.debian.3622194.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98b802a43ec9b5db250ac00c330b28aae66fa23a3517d647ca534dd75dbbbcbb
|
3 |
+
size 7707
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0a4f56674f8158c153559cb00991d39e9e1da7258c61422695c423d072e36a2
|
3 |
+
size 5368
|