Training in progress, step 2000
Browse files- last-checkpoint/config.json +40 -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 +48 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- stderr.slurm +0 -0
- stdout.slurm +4 -0
- training_args.bin +1 -1
last-checkpoint/config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DeepESP/gpt2-spanish",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.18.0",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 50257
|
40 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce0a9b8e781a9adc7b5206dce36c417fd75247f48535f73b8a0ff22cd1819064
|
3 |
+
size 995604017
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f47f80fd3abb09376d66de448ae040a39e35f293dd81734c87eb836d4bd0ff71
|
3 |
+
size 510396521
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7d28830c94d92b6d19326a0184936f2862087877e8af1a427622e66aefb96fa
|
3 |
+
size 14503
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0da848d6aca6f5529d88e638c4fb471ab39c2f011f2295ed728f24a9ae6b4786
|
3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 3.926462411880493,
|
3 |
+
"best_model_checkpoint": "./ES_corlec/checkpoint-2000",
|
4 |
+
"epoch": 0.3965107057890563,
|
5 |
+
"global_step": 2000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 1.9880573248407645e-05,
|
13 |
+
"loss": 4.1429,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.2,
|
18 |
+
"learning_rate": 1.9681528662420383e-05,
|
19 |
+
"loss": 3.7366,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.3,
|
24 |
+
"learning_rate": 1.9482484076433124e-05,
|
25 |
+
"loss": 3.5836,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.4,
|
30 |
+
"learning_rate": 1.9283439490445862e-05,
|
31 |
+
"loss": 3.4588,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.4,
|
36 |
+
"eval_loss": 3.926462411880493,
|
37 |
+
"eval_runtime": 958.5106,
|
38 |
+
"eval_samples_per_second": 42.233,
|
39 |
+
"eval_steps_per_second": 2.641,
|
40 |
+
"step": 2000
|
41 |
+
}
|
42 |
+
],
|
43 |
+
"max_steps": 50440,
|
44 |
+
"num_train_epochs": 10,
|
45 |
+
"total_flos": 2449612800000000.0,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": null
|
48 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f92189c0b6c23d5f9d7c3d130adcc7471dc4c86b70cac88476f76de70c090a5a
|
3 |
+
size 3055
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510396521
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f47f80fd3abb09376d66de448ae040a39e35f293dd81734c87eb836d4bd0ff71
|
3 |
size 510396521
|
stderr.slurm
ADDED
The diff for this file is too large to render.
See raw diff
|
|
stdout.slurm
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{'loss': 4.1429, 'learning_rate': 1.9880573248407645e-05, 'epoch': 0.1}
|
2 |
+
{'loss': 3.7366, 'learning_rate': 1.9681528662420383e-05, 'epoch': 0.2}
|
3 |
+
{'loss': 3.5836, 'learning_rate': 1.9482484076433124e-05, 'epoch': 0.3}
|
4 |
+
{'loss': 3.4588, 'learning_rate': 1.9283439490445862e-05, 'epoch': 0.4}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f92189c0b6c23d5f9d7c3d130adcc7471dc4c86b70cac88476f76de70c090a5a
|
3 |
size 3055
|