yasminesarraj commited on
Commit
b5d0790
1 Parent(s): dc414aa

Upload 10 files

Browse files
checkpoint-1842/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.26.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-1842/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.26.1"
7
+ }
checkpoint-1842/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd255084197ec4a983823f381e127a0929fde5537f720eecdba7d715601ac58
3
+ size 615796549
checkpoint-1842/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb41bbf2fdb86bcb493d58b0d86e02a1cf2e51d51b439975abc632576886ce7
3
+ size 307907461
checkpoint-1842/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc8c91fa5d535f8934dfb59e164f88fc8c07aaa4a3d2903c110cab9db713a06
3
+ size 13553
checkpoint-1842/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc7fcf0ad1a1a7d70016fb472c20b2122d1dcd5ee9d90dc135f3b09d9cf2e6b
3
+ size 627
checkpoint-1842/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.664982557296753,
3
+ "best_model_checkpoint": "flan-t5-small-samsum/checkpoint-1842",
4
+ "epoch": 1.0,
5
+ "global_step": 1842,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.27,
12
+ "learning_rate": 4.728555917480999e-05,
13
+ "loss": 1.859,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.54,
18
+ "learning_rate": 4.457111834961998e-05,
19
+ "loss": 1.829,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.81,
24
+ "learning_rate": 4.185667752442997e-05,
25
+ "loss": 1.8116,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_gen_len": 16.714285714285715,
31
+ "eval_loss": 1.664982557296753,
32
+ "eval_rouge1": 42.222,
33
+ "eval_rouge2": 18.4934,
34
+ "eval_rougeL": 35.0441,
35
+ "eval_rougeLsum": 38.4529,
36
+ "eval_runtime": 232.334,
37
+ "eval_samples_per_second": 3.525,
38
+ "eval_steps_per_second": 0.443,
39
+ "step": 1842
40
+ }
41
+ ],
42
+ "max_steps": 9210,
43
+ "num_train_epochs": 5,
44
+ "total_flos": 2738538915299328.0,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
checkpoint-1842/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9452b3c18c3b9ad15e14c16c86ba534493de85deb32e96d16e982ff7838f7f93
3
+ size 3579
logs/1678646118.59604/events.out.tfevents.1678646118.Yasmines-MacBook-Air.local.71667.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba045f33116ebb424fd17ef4a9496b4377ec8e0506b0b09e32b80652dbcd537
3
+ size 5947
logs/events.out.tfevents.1678646118.Yasmines-MacBook-Air.local.71667.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc928e34bb7a2d2bed881a9888c22e97c02060573053c4125823dd6b6990645
3
+ size 6304