“Alok”
commited on
Commit
•
b64b4c5
1
Parent(s):
29518b8
“baseline-0.12”
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +17 -3
- vocab.json +1 -1
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490396935
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9997db3d1aa7e91d59194ed88dd00efdcb48cc3e53a162ebaca3bf529dc6e83e
|
3 |
size 2490396935
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262093719
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc82d16cc6243cb5aff03286aab2ecc8d37326aa4bbdd41b8b084db5e8e2043
|
3 |
size 1262093719
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8efad1da2b331323574836ca1381491bc280164c8986ed13a689a6cf5a52d6c7
|
3 |
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -76,11 +76,25 @@
|
|
76 |
"eval_samples_per_second": 10.232,
|
77 |
"eval_wer": 0.41836158192090395,
|
78 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
}
|
80 |
],
|
81 |
"max_steps": 30800,
|
82 |
"num_train_epochs": 100,
|
83 |
-
"total_flos":
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|
86 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.790923824959481,
|
5 |
+
"global_step": 2400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
76 |
"eval_samples_per_second": 10.232,
|
77 |
"eval_wer": 0.41836158192090395,
|
78 |
"step": 2000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 7.79,
|
82 |
+
"learning_rate": 0.00028118811881188116,
|
83 |
+
"loss": 0.2992,
|
84 |
+
"step": 2400
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 7.79,
|
88 |
+
"eval_loss": 0.34237322211265564,
|
89 |
+
"eval_runtime": 196.6598,
|
90 |
+
"eval_samples_per_second": 10.124,
|
91 |
+
"eval_wer": 0.40293785310734465,
|
92 |
+
"step": 2400
|
93 |
}
|
94 |
],
|
95 |
"max_steps": 30800,
|
96 |
"num_train_epochs": 100,
|
97 |
+
"total_flos": 8.237450774585993e+18,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"e": 0, "l": 1, "x": 2, "h": 3, "7": 4, "1": 5, "c": 6, "p": 7, "_": 8, "s": 9, "y": 10, "v": 11, "f": 12, "t": 13, "u": 14, "o": 15, "j": 16, "9": 17, "i": 18, "5": 19, "d": 20, "b": 21, "2": 22, "k": 23, "'": 24, "w": 25, "q": 27, "n": 28, "0": 29, "a": 30, "r": 31, "6": 32, "m": 33, "z": 34, "3": 35, "g": 36, "|": 26, "[UNK]": 37, "[PAD]": 38}
|