Training in progress, step 500, checkpoint
Browse files- last-checkpoint/config.json +61 -0
- last-checkpoint/generation_config.json +7 -0
- last-checkpoint/global_step500/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/latest +1 -1
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/trainer_state.json +11 -17
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 6,
|
22 |
+
"num_heads": 8,
|
23 |
+
"num_layers": 6,
|
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 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.33.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
last-checkpoint/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": "4.33.1"
|
7 |
+
}
|
last-checkpoint/global_step500/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83e8739b47bd77f214d2265d8e968c48d849b22085a58dab0b7c3ccba438581f
|
3 |
+
size 77125
|
last-checkpoint/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:599deb700a2f4c61b7adc819874dd469192f52018cb4b875128a64fded13d9a9
|
3 |
+
size 181523565
|
last-checkpoint/global_step500/zero_pp_rank_1_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3929c020a78a4a0cce2c67df9b850d5a86b92225a7630a32fc9483f43ac91f92
|
3 |
+
size 76997
|
last-checkpoint/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f07594c86e8871c23855f2a19cdc79eb85f0e7d5d721efc1b9881baf6e0eb19b
|
3 |
+
size 181523565
|
last-checkpoint/global_step500/zero_pp_rank_2_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f75706537bfb250662e279566323ce34f592140890e541fbc25136c94fdeb5ad
|
3 |
+
size 76997
|
last-checkpoint/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0029132f861e09e7eab38a0ce01efab1b1df833de23e0e43184d00cf1fa8c75a
|
3 |
+
size 181523565
|
last-checkpoint/global_step500/zero_pp_rank_3_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:987560874e3a316caeab90a1bff849cb8577dcb826748a624e94454e6657bc81
|
3 |
+
size 76997
|
last-checkpoint/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bca6522f0189356f28382d62016ab596ac3ecc5570fdaf78143aeec62e2855e6
|
3 |
+
size 181523565
|
last-checkpoint/latest
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
global_step500
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481596c94b33296e9ed55da626f3e03b5bea14ef8b76b47930fb60b0bc92309e
|
3 |
+
size 242070038
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c1308702d9b086a5f1f3508e8349ed8fd156bcbf917cc570469986ebf544b9
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a686bae368655e506dce0c104615593cc3990e826fa497b96df4f213df009708
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f82111dd01fcc7a0012f668d56030cec3e7d214b8fb3347d56acb344101f8d5
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5f70bbd4c2166937b01de500ebb8e2d351aea43a0dd44583afdaabc82d411b5
|
3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,31 +1,25 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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
|
13 |
-
"learning_rate": 0.
|
14 |
-
"loss": 0.
|
15 |
-
"step":
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"epoch": 0.78,
|
19 |
-
"learning_rate": 0.0001,
|
20 |
-
"loss": 0.1473,
|
21 |
-
"step": 2000
|
22 |
}
|
23 |
],
|
24 |
-
"logging_steps":
|
25 |
-
"max_steps":
|
26 |
-
"num_train_epochs":
|
27 |
-
"save_steps":
|
28 |
-
"total_flos":
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
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": 2.0,
|
13 |
+
"learning_rate": 0.01,
|
14 |
+
"loss": 0.6125,
|
15 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
+
"logging_steps": 500,
|
19 |
+
"max_steps": 2500,
|
20 |
+
"num_train_epochs": 10,
|
21 |
+
"save_steps": 500,
|
22 |
+
"total_flos": 84516077568.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8639ef87c97e0b1db1451ec2c0e630582811a1a01d4762880d5387664e980641
|
3 |
size 6840
|