emrecanacikgoz
commited on
Commit
•
5a3f069
1
Parent(s):
19f2e80
Upload 5 files
Browse files- config.json +31 -0
- generation_config.json +7 -0
- rng_state.pth +3 -0
- trainer_state.json +86 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-125M",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": true,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 3072,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"prefix": "</s>",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.28.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50272,
|
30 |
+
"word_embed_proj_dim": 768
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2260592241a0d98e7a0509cf4763d9f1ce03f6cbe595c0119a72448b381fa14e
|
3 |
+
size 14575
|
trainer_state.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.864417568427753,
|
5 |
+
"global_step": 4500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.32,
|
12 |
+
"learning_rate": 4.469552302143009e-05,
|
13 |
+
"loss": 3.9931,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.64,
|
18 |
+
"learning_rate": 3.9391046042860174e-05,
|
19 |
+
"loss": 3.5268,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.95,
|
24 |
+
"learning_rate": 3.408656906429026e-05,
|
25 |
+
"loss": 3.2464,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"eval_loss": 3.909851312637329,
|
31 |
+
"eval_runtime": 0.2776,
|
32 |
+
"eval_samples_per_second": 205.333,
|
33 |
+
"eval_steps_per_second": 104.468,
|
34 |
+
"step": 1571
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 1.27,
|
38 |
+
"learning_rate": 2.8782092085720346e-05,
|
39 |
+
"loss": 2.4823,
|
40 |
+
"step": 2000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 1.59,
|
44 |
+
"learning_rate": 2.3477615107150435e-05,
|
45 |
+
"loss": 2.3432,
|
46 |
+
"step": 2500
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.91,
|
50 |
+
"learning_rate": 1.817313812858052e-05,
|
51 |
+
"loss": 2.2658,
|
52 |
+
"step": 3000
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 2.0,
|
56 |
+
"eval_loss": 3.7735772132873535,
|
57 |
+
"eval_runtime": 0.3496,
|
58 |
+
"eval_samples_per_second": 163.04,
|
59 |
+
"eval_steps_per_second": 82.95,
|
60 |
+
"step": 3142
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 2.23,
|
64 |
+
"learning_rate": 1.286866115001061e-05,
|
65 |
+
"loss": 1.8291,
|
66 |
+
"step": 3500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.55,
|
70 |
+
"learning_rate": 7.564184171440697e-06,
|
71 |
+
"loss": 1.6394,
|
72 |
+
"step": 4000
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.86,
|
76 |
+
"learning_rate": 2.259707192870783e-06,
|
77 |
+
"loss": 1.611,
|
78 |
+
"step": 4500
|
79 |
+
}
|
80 |
+
],
|
81 |
+
"max_steps": 4713,
|
82 |
+
"num_train_epochs": 3,
|
83 |
+
"total_flos": 133475318784000.0,
|
84 |
+
"trial_name": null,
|
85 |
+
"trial_params": null
|
86 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8019942490a39dddfe746de26e78558aa46ed512ad7d797c59d01a4b577ac590
|
3 |
+
size 3579
|