Add model files
Browse files- all_results.json +15 -0
- config.json +76 -0
- preprocessor_config.json +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +15 -0
- trainer_state.json +1187 -0
- training_args.bin +3 -0
- vocab.json +1 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 51608,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 18306,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 1263971328,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"total_flos": 1.1283763966907363e+19,
|
| 8 |
+
"train_mem_cpu_alloc_delta": 0,
|
| 9 |
+
"train_mem_cpu_peaked_delta": 0,
|
| 10 |
+
"train_mem_gpu_alloc_delta": 6388342272,
|
| 11 |
+
"train_mem_gpu_peaked_delta": 0,
|
| 12 |
+
"train_runtime": 24181.2335,
|
| 13 |
+
"train_samples": 3717,
|
| 14 |
+
"train_samples_per_second": 0.072
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/workspace/data2/el/wav2vec2-large-xlsr-greek/checkpoint-1740",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Wav2Vec2ForCTC"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"conv_bias": true,
|
| 11 |
+
"conv_dim": [
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512
|
| 19 |
+
],
|
| 20 |
+
"conv_kernel": [
|
| 21 |
+
10,
|
| 22 |
+
3,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
2,
|
| 27 |
+
2
|
| 28 |
+
],
|
| 29 |
+
"conv_stride": [
|
| 30 |
+
5,
|
| 31 |
+
2,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2
|
| 37 |
+
],
|
| 38 |
+
"ctc_loss_reduction": "mean",
|
| 39 |
+
"ctc_zero_infinity": false,
|
| 40 |
+
"do_stable_layer_norm": true,
|
| 41 |
+
"eos_token_id": 2,
|
| 42 |
+
"feat_extract_activation": "gelu",
|
| 43 |
+
"feat_extract_dropout": 0.0,
|
| 44 |
+
"feat_extract_norm": "layer",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"final_dropout": 0.0,
|
| 47 |
+
"gradient_checkpointing": true,
|
| 48 |
+
"hidden_act": "gelu",
|
| 49 |
+
"hidden_dropout": 0.1,
|
| 50 |
+
"hidden_size": 1024,
|
| 51 |
+
"initializer_range": 0.02,
|
| 52 |
+
"intermediate_size": 4096,
|
| 53 |
+
"layer_norm_eps": 1e-05,
|
| 54 |
+
"layerdrop": 0.1,
|
| 55 |
+
"mask_channel_length": 10,
|
| 56 |
+
"mask_channel_min_space": 1,
|
| 57 |
+
"mask_channel_other": 0.0,
|
| 58 |
+
"mask_channel_prob": 0.0,
|
| 59 |
+
"mask_channel_selection": "static",
|
| 60 |
+
"mask_feature_length": 10,
|
| 61 |
+
"mask_feature_prob": 0.0,
|
| 62 |
+
"mask_time_length": 10,
|
| 63 |
+
"mask_time_min_space": 1,
|
| 64 |
+
"mask_time_other": 0.0,
|
| 65 |
+
"mask_time_prob": 0.05,
|
| 66 |
+
"mask_time_selection": "static",
|
| 67 |
+
"model_type": "wav2vec2",
|
| 68 |
+
"num_attention_heads": 16,
|
| 69 |
+
"num_conv_pos_embedding_groups": 16,
|
| 70 |
+
"num_conv_pos_embeddings": 128,
|
| 71 |
+
"num_feat_extract_layers": 7,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"pad_token_id": 52,
|
| 74 |
+
"transformers_version": "4.5.0.dev0",
|
| 75 |
+
"vocab_size": 53
|
| 76 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_size": 1,
|
| 4 |
+
"padding_side": "right",
|
| 5 |
+
"padding_value": 0.0,
|
| 6 |
+
"return_attention_mask": true,
|
| 7 |
+
"sampling_rate": 16000
|
| 8 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41b50f52daeec4f293eca02ac9fda54c0214f7bc888f7bdeabf5d40fd90fb522
|
| 3 |
+
size 1262151127
|
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": "|"}
|
train_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 51608,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 18306,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 1263971328,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"total_flos": 1.1283763966907363e+19,
|
| 8 |
+
"train_mem_cpu_alloc_delta": 0,
|
| 9 |
+
"train_mem_cpu_peaked_delta": 0,
|
| 10 |
+
"train_mem_gpu_alloc_delta": 6388342272,
|
| 11 |
+
"train_mem_gpu_peaked_delta": 0,
|
| 12 |
+
"train_runtime": 24181.2335,
|
| 13 |
+
"train_samples": 3717,
|
| 14 |
+
"train_samples_per_second": 0.072
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.47945896840617747,
|
| 3 |
+
"best_model_checkpoint": "/workspace/data2/el/wav2vec2-large-xlsr-greek/checkpoint-1740",
|
| 4 |
+
"epoch": 14.995708154506438,
|
| 5 |
+
"global_step": 1740,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 0.00015,
|
| 13 |
+
"loss": 18.1246,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 0.0003,
|
| 19 |
+
"loss": 16.1703,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 0.0002946428571428571,
|
| 25 |
+
"loss": 6.2477,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 0.00028928571428571425,
|
| 31 |
+
"loss": 3.5827,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.43,
|
| 36 |
+
"learning_rate": 0.00028392857142857137,
|
| 37 |
+
"loss": 3.2333,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 0.00027857142857142854,
|
| 43 |
+
"loss": 3.1704,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"learning_rate": 0.0002732142857142857,
|
| 49 |
+
"loss": 3.1395,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.69,
|
| 54 |
+
"learning_rate": 0.00026785714285714287,
|
| 55 |
+
"loss": 3.1397,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.77,
|
| 60 |
+
"learning_rate": 0.0002625,
|
| 61 |
+
"loss": 3.1298,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.86,
|
| 66 |
+
"learning_rate": 0.0002571428571428571,
|
| 67 |
+
"loss": 3.1082,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.94,
|
| 72 |
+
"learning_rate": 0.00025178571428571426,
|
| 73 |
+
"loss": 3.0917,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_loss": 3.068535089492798,
|
| 79 |
+
"eval_runtime": 645.4744,
|
| 80 |
+
"eval_samples_per_second": 2.358,
|
| 81 |
+
"eval_wer": 1.0,
|
| 82 |
+
"step": 116
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.03,
|
| 86 |
+
"learning_rate": 0.0002464285714285714,
|
| 87 |
+
"loss": 3.2085,
|
| 88 |
+
"step": 120
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.12,
|
| 92 |
+
"learning_rate": 0.00024107142857142857,
|
| 93 |
+
"loss": 3.0118,
|
| 94 |
+
"step": 130
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.21,
|
| 98 |
+
"learning_rate": 0.00023571428571428569,
|
| 99 |
+
"loss": 3.0139,
|
| 100 |
+
"step": 140
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.29,
|
| 104 |
+
"learning_rate": 0.00023035714285714285,
|
| 105 |
+
"loss": 3.0176,
|
| 106 |
+
"step": 150
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.38,
|
| 110 |
+
"learning_rate": 0.000225,
|
| 111 |
+
"loss": 2.9979,
|
| 112 |
+
"step": 160
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.46,
|
| 116 |
+
"learning_rate": 0.0002196428571428571,
|
| 117 |
+
"loss": 2.9721,
|
| 118 |
+
"step": 170
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.55,
|
| 122 |
+
"learning_rate": 0.00021428571428571427,
|
| 123 |
+
"loss": 2.9585,
|
| 124 |
+
"step": 180
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.64,
|
| 128 |
+
"learning_rate": 0.0002089285714285714,
|
| 129 |
+
"loss": 2.9578,
|
| 130 |
+
"step": 190
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.72,
|
| 134 |
+
"learning_rate": 0.00020357142857142856,
|
| 135 |
+
"loss": 2.9347,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.81,
|
| 140 |
+
"learning_rate": 0.0001982142857142857,
|
| 141 |
+
"loss": 2.9348,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.89,
|
| 146 |
+
"learning_rate": 0.00019285714285714286,
|
| 147 |
+
"loss": 2.9156,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.98,
|
| 152 |
+
"learning_rate": 0.00018749999999999998,
|
| 153 |
+
"loss": 2.8911,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.0,
|
| 158 |
+
"eval_loss": 2.9123377799987793,
|
| 159 |
+
"eval_runtime": 651.1025,
|
| 160 |
+
"eval_samples_per_second": 2.338,
|
| 161 |
+
"eval_wer": 1.0,
|
| 162 |
+
"step": 232
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.07,
|
| 166 |
+
"learning_rate": 0.00018214285714285712,
|
| 167 |
+
"loss": 3.002,
|
| 168 |
+
"step": 240
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.15,
|
| 172 |
+
"learning_rate": 0.00017678571428571428,
|
| 173 |
+
"loss": 2.7696,
|
| 174 |
+
"step": 250
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.24,
|
| 178 |
+
"learning_rate": 0.0001714285714285714,
|
| 179 |
+
"loss": 2.6308,
|
| 180 |
+
"step": 260
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.33,
|
| 184 |
+
"learning_rate": 0.00016607142857142857,
|
| 185 |
+
"loss": 2.3949,
|
| 186 |
+
"step": 270
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.41,
|
| 190 |
+
"learning_rate": 0.0001607142857142857,
|
| 191 |
+
"loss": 2.0719,
|
| 192 |
+
"step": 280
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.5,
|
| 196 |
+
"learning_rate": 0.00015535714285714285,
|
| 197 |
+
"loss": 1.7915,
|
| 198 |
+
"step": 290
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.58,
|
| 202 |
+
"learning_rate": 0.00015,
|
| 203 |
+
"loss": 1.5479,
|
| 204 |
+
"step": 300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.67,
|
| 208 |
+
"learning_rate": 0.00014464285714285713,
|
| 209 |
+
"loss": 1.4167,
|
| 210 |
+
"step": 310
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.76,
|
| 214 |
+
"learning_rate": 0.00013928571428571427,
|
| 215 |
+
"loss": 1.2183,
|
| 216 |
+
"step": 320
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.84,
|
| 220 |
+
"learning_rate": 0.00013392857142857144,
|
| 221 |
+
"loss": 1.1713,
|
| 222 |
+
"step": 330
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.93,
|
| 226 |
+
"learning_rate": 0.00012857142857142855,
|
| 227 |
+
"loss": 1.0325,
|
| 228 |
+
"step": 340
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.0,
|
| 232 |
+
"eval_loss": 0.8776374459266663,
|
| 233 |
+
"eval_runtime": 651.452,
|
| 234 |
+
"eval_samples_per_second": 2.336,
|
| 235 |
+
"eval_wer": 0.8105380034319168,
|
| 236 |
+
"step": 348
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.02,
|
| 240 |
+
"learning_rate": 0.0001232142857142857,
|
| 241 |
+
"loss": 0.9978,
|
| 242 |
+
"step": 350
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.1,
|
| 246 |
+
"learning_rate": 0.00011785714285714284,
|
| 247 |
+
"loss": 0.8941,
|
| 248 |
+
"step": 360
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.19,
|
| 252 |
+
"learning_rate": 0.0001125,
|
| 253 |
+
"loss": 0.875,
|
| 254 |
+
"step": 370
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.27,
|
| 258 |
+
"learning_rate": 0.00010714285714285714,
|
| 259 |
+
"loss": 0.801,
|
| 260 |
+
"step": 380
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.36,
|
| 264 |
+
"learning_rate": 0.00010178571428571428,
|
| 265 |
+
"loss": 0.7847,
|
| 266 |
+
"step": 390
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.45,
|
| 270 |
+
"learning_rate": 9.642857142857143e-05,
|
| 271 |
+
"loss": 0.6949,
|
| 272 |
+
"step": 400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.53,
|
| 276 |
+
"learning_rate": 9.107142857142856e-05,
|
| 277 |
+
"loss": 0.7307,
|
| 278 |
+
"step": 410
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.62,
|
| 282 |
+
"learning_rate": 8.57142857142857e-05,
|
| 283 |
+
"loss": 0.6729,
|
| 284 |
+
"step": 420
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.7,
|
| 288 |
+
"learning_rate": 8.035714285714285e-05,
|
| 289 |
+
"loss": 0.6699,
|
| 290 |
+
"step": 430
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.79,
|
| 294 |
+
"learning_rate": 7.5e-05,
|
| 295 |
+
"loss": 0.6768,
|
| 296 |
+
"step": 440
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.88,
|
| 300 |
+
"learning_rate": 6.964285714285713e-05,
|
| 301 |
+
"loss": 0.6459,
|
| 302 |
+
"step": 450
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.96,
|
| 306 |
+
"learning_rate": 6.428571428571427e-05,
|
| 307 |
+
"loss": 0.6589,
|
| 308 |
+
"step": 460
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.0,
|
| 312 |
+
"eval_loss": 0.6442593336105347,
|
| 313 |
+
"eval_runtime": 653.4327,
|
| 314 |
+
"eval_samples_per_second": 2.329,
|
| 315 |
+
"eval_wer": 0.7133340062582013,
|
| 316 |
+
"step": 464
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 4.05,
|
| 320 |
+
"learning_rate": 5.892857142857142e-05,
|
| 321 |
+
"loss": 0.6647,
|
| 322 |
+
"step": 470
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.14,
|
| 326 |
+
"learning_rate": 5.357142857142857e-05,
|
| 327 |
+
"loss": 0.6859,
|
| 328 |
+
"step": 480
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.22,
|
| 332 |
+
"learning_rate": 4.8214285714285716e-05,
|
| 333 |
+
"loss": 0.6298,
|
| 334 |
+
"step": 490
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.31,
|
| 338 |
+
"learning_rate": 4.285714285714285e-05,
|
| 339 |
+
"loss": 0.6076,
|
| 340 |
+
"step": 500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.39,
|
| 344 |
+
"learning_rate": 3.75e-05,
|
| 345 |
+
"loss": 0.5485,
|
| 346 |
+
"step": 510
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.48,
|
| 350 |
+
"learning_rate": 3.214285714285714e-05,
|
| 351 |
+
"loss": 0.5852,
|
| 352 |
+
"step": 520
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.57,
|
| 356 |
+
"learning_rate": 2.6785714285714284e-05,
|
| 357 |
+
"loss": 0.5452,
|
| 358 |
+
"step": 530
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.65,
|
| 362 |
+
"learning_rate": 2.1428571428571425e-05,
|
| 363 |
+
"loss": 0.5593,
|
| 364 |
+
"step": 540
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.74,
|
| 368 |
+
"learning_rate": 1.607142857142857e-05,
|
| 369 |
+
"loss": 0.5316,
|
| 370 |
+
"step": 550
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.82,
|
| 374 |
+
"learning_rate": 1.0714285714285712e-05,
|
| 375 |
+
"loss": 0.5742,
|
| 376 |
+
"step": 560
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 4.91,
|
| 380 |
+
"learning_rate": 5.357142857142856e-06,
|
| 381 |
+
"loss": 0.5978,
|
| 382 |
+
"step": 570
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 5.0,
|
| 386 |
+
"learning_rate": 0.0,
|
| 387 |
+
"loss": 0.5398,
|
| 388 |
+
"step": 580
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.0,
|
| 392 |
+
"eval_loss": 0.6011346578598022,
|
| 393 |
+
"eval_runtime": 660.5778,
|
| 394 |
+
"eval_samples_per_second": 2.304,
|
| 395 |
+
"eval_wer": 0.687998384980317,
|
| 396 |
+
"step": 580
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.09,
|
| 400 |
+
"learning_rate": 0.0002005813953488372,
|
| 401 |
+
"loss": 0.5457,
|
| 402 |
+
"step": 590
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.17,
|
| 406 |
+
"learning_rate": 0.00019883720930232555,
|
| 407 |
+
"loss": 0.5124,
|
| 408 |
+
"step": 600
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.26,
|
| 412 |
+
"learning_rate": 0.00019709302325581393,
|
| 413 |
+
"loss": 0.5249,
|
| 414 |
+
"step": 610
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.34,
|
| 418 |
+
"learning_rate": 0.00019534883720930232,
|
| 419 |
+
"loss": 0.5133,
|
| 420 |
+
"step": 620
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.43,
|
| 424 |
+
"learning_rate": 0.00019360465116279068,
|
| 425 |
+
"loss": 0.5288,
|
| 426 |
+
"step": 630
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.52,
|
| 430 |
+
"learning_rate": 0.00019186046511627906,
|
| 431 |
+
"loss": 0.544,
|
| 432 |
+
"step": 640
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.6,
|
| 436 |
+
"learning_rate": 0.00019011627906976742,
|
| 437 |
+
"loss": 0.5013,
|
| 438 |
+
"step": 650
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 5.69,
|
| 442 |
+
"learning_rate": 0.0001883720930232558,
|
| 443 |
+
"loss": 0.4729,
|
| 444 |
+
"step": 660
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.77,
|
| 448 |
+
"learning_rate": 0.00018662790697674417,
|
| 449 |
+
"loss": 0.5257,
|
| 450 |
+
"step": 670
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.86,
|
| 454 |
+
"learning_rate": 0.00018488372093023253,
|
| 455 |
+
"loss": 0.5418,
|
| 456 |
+
"step": 680
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 5.94,
|
| 460 |
+
"learning_rate": 0.00018313953488372092,
|
| 461 |
+
"loss": 0.4751,
|
| 462 |
+
"step": 690
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 6.0,
|
| 466 |
+
"eval_loss": 0.5606071352958679,
|
| 467 |
+
"eval_runtime": 650.6852,
|
| 468 |
+
"eval_samples_per_second": 2.339,
|
| 469 |
+
"eval_wer": 0.630766124962148,
|
| 470 |
+
"step": 696
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.03,
|
| 474 |
+
"learning_rate": 0.00018139534883720928,
|
| 475 |
+
"loss": 0.5154,
|
| 476 |
+
"step": 700
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 6.12,
|
| 480 |
+
"learning_rate": 0.00017965116279069763,
|
| 481 |
+
"loss": 0.4327,
|
| 482 |
+
"step": 710
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.21,
|
| 486 |
+
"learning_rate": 0.00017790697674418605,
|
| 487 |
+
"loss": 0.4265,
|
| 488 |
+
"step": 720
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.29,
|
| 492 |
+
"learning_rate": 0.0001761627906976744,
|
| 493 |
+
"loss": 0.4695,
|
| 494 |
+
"step": 730
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.38,
|
| 498 |
+
"learning_rate": 0.0001744186046511628,
|
| 499 |
+
"loss": 0.4606,
|
| 500 |
+
"step": 740
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.46,
|
| 504 |
+
"learning_rate": 0.00017267441860465115,
|
| 505 |
+
"loss": 0.4286,
|
| 506 |
+
"step": 750
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.55,
|
| 510 |
+
"learning_rate": 0.0001709302325581395,
|
| 511 |
+
"loss": 0.4215,
|
| 512 |
+
"step": 760
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.64,
|
| 516 |
+
"learning_rate": 0.0001691860465116279,
|
| 517 |
+
"loss": 0.4614,
|
| 518 |
+
"step": 770
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.72,
|
| 522 |
+
"learning_rate": 0.00016744186046511626,
|
| 523 |
+
"loss": 0.4296,
|
| 524 |
+
"step": 780
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.81,
|
| 528 |
+
"learning_rate": 0.00016569767441860464,
|
| 529 |
+
"loss": 0.4462,
|
| 530 |
+
"step": 790
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.89,
|
| 534 |
+
"learning_rate": 0.000163953488372093,
|
| 535 |
+
"loss": 0.4255,
|
| 536 |
+
"step": 800
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.98,
|
| 540 |
+
"learning_rate": 0.00016220930232558136,
|
| 541 |
+
"loss": 0.4463,
|
| 542 |
+
"step": 810
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 7.0,
|
| 546 |
+
"eval_loss": 0.5151863694190979,
|
| 547 |
+
"eval_runtime": 657.3854,
|
| 548 |
+
"eval_samples_per_second": 2.315,
|
| 549 |
+
"eval_wer": 0.5907943878066014,
|
| 550 |
+
"step": 812
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 7.07,
|
| 554 |
+
"learning_rate": 0.00016046511627906975,
|
| 555 |
+
"loss": 0.4279,
|
| 556 |
+
"step": 820
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 7.15,
|
| 560 |
+
"learning_rate": 0.00015872093023255814,
|
| 561 |
+
"loss": 0.3671,
|
| 562 |
+
"step": 830
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.24,
|
| 566 |
+
"learning_rate": 0.00015697674418604652,
|
| 567 |
+
"loss": 0.3694,
|
| 568 |
+
"step": 840
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 7.33,
|
| 572 |
+
"learning_rate": 0.00015523255813953488,
|
| 573 |
+
"loss": 0.3549,
|
| 574 |
+
"step": 850
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 7.41,
|
| 578 |
+
"learning_rate": 0.00015348837209302324,
|
| 579 |
+
"loss": 0.3853,
|
| 580 |
+
"step": 860
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 7.5,
|
| 584 |
+
"learning_rate": 0.00015174418604651163,
|
| 585 |
+
"loss": 0.3637,
|
| 586 |
+
"step": 870
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 7.58,
|
| 590 |
+
"learning_rate": 0.00015,
|
| 591 |
+
"loss": 0.3457,
|
| 592 |
+
"step": 880
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 7.67,
|
| 596 |
+
"learning_rate": 0.00014825581395348835,
|
| 597 |
+
"loss": 0.3741,
|
| 598 |
+
"step": 890
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 7.76,
|
| 602 |
+
"learning_rate": 0.00014651162790697673,
|
| 603 |
+
"loss": 0.3726,
|
| 604 |
+
"step": 900
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.84,
|
| 608 |
+
"learning_rate": 0.00014476744186046512,
|
| 609 |
+
"loss": 0.3297,
|
| 610 |
+
"step": 910
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 7.93,
|
| 614 |
+
"learning_rate": 0.00014302325581395348,
|
| 615 |
+
"loss": 0.3659,
|
| 616 |
+
"step": 920
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 8.0,
|
| 620 |
+
"eval_loss": 0.4685789942741394,
|
| 621 |
+
"eval_runtime": 658.0802,
|
| 622 |
+
"eval_samples_per_second": 2.313,
|
| 623 |
+
"eval_wer": 0.5541536287473504,
|
| 624 |
+
"step": 928
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 8.02,
|
| 628 |
+
"learning_rate": 0.00014127906976744184,
|
| 629 |
+
"loss": 0.37,
|
| 630 |
+
"step": 930
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 8.1,
|
| 634 |
+
"learning_rate": 0.00013953488372093022,
|
| 635 |
+
"loss": 0.3217,
|
| 636 |
+
"step": 940
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 8.19,
|
| 640 |
+
"learning_rate": 0.00013779069767441858,
|
| 641 |
+
"loss": 0.3995,
|
| 642 |
+
"step": 950
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 8.27,
|
| 646 |
+
"learning_rate": 0.00013604651162790697,
|
| 647 |
+
"loss": 0.351,
|
| 648 |
+
"step": 960
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 8.36,
|
| 652 |
+
"learning_rate": 0.00013430232558139533,
|
| 653 |
+
"loss": 0.298,
|
| 654 |
+
"step": 970
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 8.45,
|
| 658 |
+
"learning_rate": 0.00013255813953488372,
|
| 659 |
+
"loss": 0.2876,
|
| 660 |
+
"step": 980
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8.53,
|
| 664 |
+
"learning_rate": 0.00013081395348837207,
|
| 665 |
+
"loss": 0.3023,
|
| 666 |
+
"step": 990
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 8.62,
|
| 670 |
+
"learning_rate": 0.00012906976744186046,
|
| 671 |
+
"loss": 0.2861,
|
| 672 |
+
"step": 1000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 8.7,
|
| 676 |
+
"learning_rate": 0.00012732558139534882,
|
| 677 |
+
"loss": 0.3058,
|
| 678 |
+
"step": 1010
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 8.79,
|
| 682 |
+
"learning_rate": 0.0001255813953488372,
|
| 683 |
+
"loss": 0.3048,
|
| 684 |
+
"step": 1020
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 8.88,
|
| 688 |
+
"learning_rate": 0.00012383720930232557,
|
| 689 |
+
"loss": 0.3093,
|
| 690 |
+
"step": 1030
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 8.96,
|
| 694 |
+
"learning_rate": 0.00012209302325581395,
|
| 695 |
+
"loss": 0.2921,
|
| 696 |
+
"step": 1040
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 9.0,
|
| 700 |
+
"eval_loss": 0.4716265797615051,
|
| 701 |
+
"eval_runtime": 661.023,
|
| 702 |
+
"eval_samples_per_second": 2.302,
|
| 703 |
+
"eval_wer": 0.5510245281114363,
|
| 704 |
+
"step": 1044
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 9.05,
|
| 708 |
+
"learning_rate": 0.00012034883720930231,
|
| 709 |
+
"loss": 0.2875,
|
| 710 |
+
"step": 1050
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 9.14,
|
| 714 |
+
"learning_rate": 0.00011860465116279069,
|
| 715 |
+
"loss": 0.2854,
|
| 716 |
+
"step": 1060
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 9.22,
|
| 720 |
+
"learning_rate": 0.00011686046511627907,
|
| 721 |
+
"loss": 0.2508,
|
| 722 |
+
"step": 1070
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 9.31,
|
| 726 |
+
"learning_rate": 0.00011511627906976743,
|
| 727 |
+
"loss": 0.2777,
|
| 728 |
+
"step": 1080
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 9.39,
|
| 732 |
+
"learning_rate": 0.0001133720930232558,
|
| 733 |
+
"loss": 0.3192,
|
| 734 |
+
"step": 1090
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 9.48,
|
| 738 |
+
"learning_rate": 0.00011162790697674418,
|
| 739 |
+
"loss": 0.2474,
|
| 740 |
+
"step": 1100
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 9.57,
|
| 744 |
+
"learning_rate": 0.00010988372093023255,
|
| 745 |
+
"loss": 0.2736,
|
| 746 |
+
"step": 1110
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 9.65,
|
| 750 |
+
"learning_rate": 0.00010813953488372091,
|
| 751 |
+
"loss": 0.2469,
|
| 752 |
+
"step": 1120
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 9.74,
|
| 756 |
+
"learning_rate": 0.0001063953488372093,
|
| 757 |
+
"loss": 0.2496,
|
| 758 |
+
"step": 1130
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 9.82,
|
| 762 |
+
"learning_rate": 0.00010465116279069767,
|
| 763 |
+
"loss": 0.2333,
|
| 764 |
+
"step": 1140
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 9.91,
|
| 768 |
+
"learning_rate": 0.00010290697674418604,
|
| 769 |
+
"loss": 0.262,
|
| 770 |
+
"step": 1150
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 10.0,
|
| 774 |
+
"learning_rate": 0.0001011627906976744,
|
| 775 |
+
"loss": 0.2861,
|
| 776 |
+
"step": 1160
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 10.0,
|
| 780 |
+
"eval_loss": 0.4394018054008484,
|
| 781 |
+
"eval_runtime": 663.2479,
|
| 782 |
+
"eval_samples_per_second": 2.295,
|
| 783 |
+
"eval_wer": 0.5216513576259211,
|
| 784 |
+
"step": 1160
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 10.09,
|
| 788 |
+
"learning_rate": 9.941860465116277e-05,
|
| 789 |
+
"loss": 0.2817,
|
| 790 |
+
"step": 1170
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 10.17,
|
| 794 |
+
"learning_rate": 9.767441860465116e-05,
|
| 795 |
+
"loss": 0.257,
|
| 796 |
+
"step": 1180
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 10.26,
|
| 800 |
+
"learning_rate": 9.593023255813953e-05,
|
| 801 |
+
"loss": 0.2181,
|
| 802 |
+
"step": 1190
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 10.34,
|
| 806 |
+
"learning_rate": 9.41860465116279e-05,
|
| 807 |
+
"loss": 0.2173,
|
| 808 |
+
"step": 1200
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 10.43,
|
| 812 |
+
"learning_rate": 9.244186046511626e-05,
|
| 813 |
+
"loss": 0.261,
|
| 814 |
+
"step": 1210
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 10.52,
|
| 818 |
+
"learning_rate": 9.069767441860464e-05,
|
| 819 |
+
"loss": 0.1942,
|
| 820 |
+
"step": 1220
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 10.6,
|
| 824 |
+
"learning_rate": 8.895348837209302e-05,
|
| 825 |
+
"loss": 0.2252,
|
| 826 |
+
"step": 1230
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 10.69,
|
| 830 |
+
"learning_rate": 8.72093023255814e-05,
|
| 831 |
+
"loss": 0.2256,
|
| 832 |
+
"step": 1240
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 10.77,
|
| 836 |
+
"learning_rate": 8.546511627906976e-05,
|
| 837 |
+
"loss": 0.2071,
|
| 838 |
+
"step": 1250
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 10.86,
|
| 842 |
+
"learning_rate": 8.372093023255813e-05,
|
| 843 |
+
"loss": 0.2457,
|
| 844 |
+
"step": 1260
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 10.94,
|
| 848 |
+
"learning_rate": 8.19767441860465e-05,
|
| 849 |
+
"loss": 0.221,
|
| 850 |
+
"step": 1270
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 11.0,
|
| 854 |
+
"eval_loss": 0.42013201117515564,
|
| 855 |
+
"eval_runtime": 666.5166,
|
| 856 |
+
"eval_samples_per_second": 2.284,
|
| 857 |
+
"eval_wer": 0.508731200161502,
|
| 858 |
+
"step": 1276
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 11.03,
|
| 862 |
+
"learning_rate": 8.023255813953487e-05,
|
| 863 |
+
"loss": 0.2529,
|
| 864 |
+
"step": 1280
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 11.12,
|
| 868 |
+
"learning_rate": 7.848837209302326e-05,
|
| 869 |
+
"loss": 0.1994,
|
| 870 |
+
"step": 1290
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 11.21,
|
| 874 |
+
"learning_rate": 7.674418604651162e-05,
|
| 875 |
+
"loss": 0.2158,
|
| 876 |
+
"step": 1300
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 11.29,
|
| 880 |
+
"learning_rate": 7.5e-05,
|
| 881 |
+
"loss": 0.1888,
|
| 882 |
+
"step": 1310
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 11.38,
|
| 886 |
+
"learning_rate": 7.325581395348837e-05,
|
| 887 |
+
"loss": 0.2134,
|
| 888 |
+
"step": 1320
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 11.46,
|
| 892 |
+
"learning_rate": 7.151162790697674e-05,
|
| 893 |
+
"loss": 0.2182,
|
| 894 |
+
"step": 1330
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 11.55,
|
| 898 |
+
"learning_rate": 6.976744186046511e-05,
|
| 899 |
+
"loss": 0.2357,
|
| 900 |
+
"step": 1340
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 11.64,
|
| 904 |
+
"learning_rate": 6.802325581395348e-05,
|
| 905 |
+
"loss": 0.2091,
|
| 906 |
+
"step": 1350
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 11.72,
|
| 910 |
+
"learning_rate": 6.627906976744186e-05,
|
| 911 |
+
"loss": 0.1894,
|
| 912 |
+
"step": 1360
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 11.81,
|
| 916 |
+
"learning_rate": 6.453488372093023e-05,
|
| 917 |
+
"loss": 0.205,
|
| 918 |
+
"step": 1370
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 11.89,
|
| 922 |
+
"learning_rate": 6.27906976744186e-05,
|
| 923 |
+
"loss": 0.1775,
|
| 924 |
+
"step": 1380
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 11.98,
|
| 928 |
+
"learning_rate": 6.104651162790698e-05,
|
| 929 |
+
"loss": 0.1736,
|
| 930 |
+
"step": 1390
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 12.0,
|
| 934 |
+
"eval_loss": 0.43105581402778625,
|
| 935 |
+
"eval_runtime": 661.3357,
|
| 936 |
+
"eval_samples_per_second": 2.301,
|
| 937 |
+
"eval_wer": 0.49934389825375997,
|
| 938 |
+
"step": 1392
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 12.07,
|
| 942 |
+
"learning_rate": 5.930232558139534e-05,
|
| 943 |
+
"loss": 0.1956,
|
| 944 |
+
"step": 1400
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 12.15,
|
| 948 |
+
"learning_rate": 5.7558139534883715e-05,
|
| 949 |
+
"loss": 0.1675,
|
| 950 |
+
"step": 1410
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 12.24,
|
| 954 |
+
"learning_rate": 5.581395348837209e-05,
|
| 955 |
+
"loss": 0.2014,
|
| 956 |
+
"step": 1420
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 12.33,
|
| 960 |
+
"learning_rate": 5.4069767441860454e-05,
|
| 961 |
+
"loss": 0.1966,
|
| 962 |
+
"step": 1430
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 12.41,
|
| 966 |
+
"learning_rate": 5.2325581395348834e-05,
|
| 967 |
+
"loss": 0.1837,
|
| 968 |
+
"step": 1440
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 12.5,
|
| 972 |
+
"learning_rate": 5.05813953488372e-05,
|
| 973 |
+
"loss": 0.1972,
|
| 974 |
+
"step": 1450
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 12.58,
|
| 978 |
+
"learning_rate": 4.883720930232558e-05,
|
| 979 |
+
"loss": 0.1936,
|
| 980 |
+
"step": 1460
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 12.67,
|
| 984 |
+
"learning_rate": 4.709302325581395e-05,
|
| 985 |
+
"loss": 0.172,
|
| 986 |
+
"step": 1470
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 12.76,
|
| 990 |
+
"learning_rate": 4.534883720930232e-05,
|
| 991 |
+
"loss": 0.2008,
|
| 992 |
+
"step": 1480
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 12.84,
|
| 996 |
+
"learning_rate": 4.36046511627907e-05,
|
| 997 |
+
"loss": 0.1668,
|
| 998 |
+
"step": 1490
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 12.93,
|
| 1002 |
+
"learning_rate": 4.1860465116279065e-05,
|
| 1003 |
+
"loss": 0.1796,
|
| 1004 |
+
"step": 1500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 13.0,
|
| 1008 |
+
"eval_loss": 0.4192411005496979,
|
| 1009 |
+
"eval_runtime": 664.4607,
|
| 1010 |
+
"eval_samples_per_second": 2.291,
|
| 1011 |
+
"eval_wer": 0.48299182396285456,
|
| 1012 |
+
"step": 1508
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 13.02,
|
| 1016 |
+
"learning_rate": 4.011627906976744e-05,
|
| 1017 |
+
"loss": 0.185,
|
| 1018 |
+
"step": 1510
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 13.1,
|
| 1022 |
+
"learning_rate": 3.837209302325581e-05,
|
| 1023 |
+
"loss": 0.1469,
|
| 1024 |
+
"step": 1520
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 13.19,
|
| 1028 |
+
"learning_rate": 3.662790697674418e-05,
|
| 1029 |
+
"loss": 0.2046,
|
| 1030 |
+
"step": 1530
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 13.27,
|
| 1034 |
+
"learning_rate": 3.4883720930232556e-05,
|
| 1035 |
+
"loss": 0.1514,
|
| 1036 |
+
"step": 1540
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 13.36,
|
| 1040 |
+
"learning_rate": 3.313953488372093e-05,
|
| 1041 |
+
"loss": 0.1649,
|
| 1042 |
+
"step": 1550
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 13.45,
|
| 1046 |
+
"learning_rate": 3.13953488372093e-05,
|
| 1047 |
+
"loss": 0.1787,
|
| 1048 |
+
"step": 1560
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 13.53,
|
| 1052 |
+
"learning_rate": 2.965116279069767e-05,
|
| 1053 |
+
"loss": 0.1808,
|
| 1054 |
+
"step": 1570
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 13.62,
|
| 1058 |
+
"learning_rate": 2.7906976744186044e-05,
|
| 1059 |
+
"loss": 0.1292,
|
| 1060 |
+
"step": 1580
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 13.7,
|
| 1064 |
+
"learning_rate": 2.6162790697674417e-05,
|
| 1065 |
+
"loss": 0.1767,
|
| 1066 |
+
"step": 1590
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 13.79,
|
| 1070 |
+
"learning_rate": 2.441860465116279e-05,
|
| 1071 |
+
"loss": 0.1596,
|
| 1072 |
+
"step": 1600
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 13.88,
|
| 1076 |
+
"learning_rate": 2.267441860465116e-05,
|
| 1077 |
+
"loss": 0.2036,
|
| 1078 |
+
"step": 1610
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 13.96,
|
| 1082 |
+
"learning_rate": 2.0930232558139532e-05,
|
| 1083 |
+
"loss": 0.1593,
|
| 1084 |
+
"step": 1620
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 14.0,
|
| 1088 |
+
"eval_loss": 0.42025962471961975,
|
| 1089 |
+
"eval_runtime": 664.1839,
|
| 1090 |
+
"eval_samples_per_second": 2.292,
|
| 1091 |
+
"eval_wer": 0.4830927626930453,
|
| 1092 |
+
"step": 1624
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 14.05,
|
| 1096 |
+
"learning_rate": 1.9186046511627905e-05,
|
| 1097 |
+
"loss": 0.1429,
|
| 1098 |
+
"step": 1630
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 14.14,
|
| 1102 |
+
"learning_rate": 1.7441860465116278e-05,
|
| 1103 |
+
"loss": 0.1558,
|
| 1104 |
+
"step": 1640
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 14.22,
|
| 1108 |
+
"learning_rate": 1.569767441860465e-05,
|
| 1109 |
+
"loss": 0.1598,
|
| 1110 |
+
"step": 1650
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 14.31,
|
| 1114 |
+
"learning_rate": 1.3953488372093022e-05,
|
| 1115 |
+
"loss": 0.1598,
|
| 1116 |
+
"step": 1660
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 14.39,
|
| 1120 |
+
"learning_rate": 1.2209302325581395e-05,
|
| 1121 |
+
"loss": 0.1742,
|
| 1122 |
+
"step": 1670
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 14.48,
|
| 1126 |
+
"learning_rate": 1.0465116279069766e-05,
|
| 1127 |
+
"loss": 0.1402,
|
| 1128 |
+
"step": 1680
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 14.57,
|
| 1132 |
+
"learning_rate": 8.720930232558139e-06,
|
| 1133 |
+
"loss": 0.163,
|
| 1134 |
+
"step": 1690
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 14.65,
|
| 1138 |
+
"learning_rate": 6.976744186046511e-06,
|
| 1139 |
+
"loss": 0.2057,
|
| 1140 |
+
"step": 1700
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 14.74,
|
| 1144 |
+
"learning_rate": 5.232558139534883e-06,
|
| 1145 |
+
"loss": 0.157,
|
| 1146 |
+
"step": 1710
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 14.82,
|
| 1150 |
+
"learning_rate": 3.4883720930232555e-06,
|
| 1151 |
+
"loss": 0.1471,
|
| 1152 |
+
"step": 1720
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 14.91,
|
| 1156 |
+
"learning_rate": 1.7441860465116278e-06,
|
| 1157 |
+
"loss": 0.2013,
|
| 1158 |
+
"step": 1730
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 15.0,
|
| 1162 |
+
"learning_rate": 0.0,
|
| 1163 |
+
"loss": 0.167,
|
| 1164 |
+
"step": 1740
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 15.0,
|
| 1168 |
+
"eval_loss": 0.417759507894516,
|
| 1169 |
+
"eval_runtime": 663.3111,
|
| 1170 |
+
"eval_samples_per_second": 2.295,
|
| 1171 |
+
"eval_wer": 0.47945896840617747,
|
| 1172 |
+
"step": 1740
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 15.0,
|
| 1176 |
+
"step": 1740,
|
| 1177 |
+
"total_flos": 1.1283763966907363e+19,
|
| 1178 |
+
"train_runtime": 24181.2335,
|
| 1179 |
+
"train_samples_per_second": 0.072
|
| 1180 |
+
}
|
| 1181 |
+
],
|
| 1182 |
+
"max_steps": 1740,
|
| 1183 |
+
"num_train_epochs": 15,
|
| 1184 |
+
"total_flos": 1.1283763966907363e+19,
|
| 1185 |
+
"trial_name": null,
|
| 1186 |
+
"trial_params": null
|
| 1187 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8df986de605c23da253f3c1b3ebbc40d3e0a361f925f38c7b898f73cbb5679b
|
| 3 |
+
size 2351
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"σ": 0, "δ": 1, "γ": 2, "«": 3, "ώ": 4, "θ": 5, "r": 6, "τ": 7, "ή": 8, "»": 9, "ι": 10, "ΐ": 11, "φ": 12, "m": 13, "h": 14, "ί": 15, "π": 16, "n": 17, "´": 18, "λ": 19, "η": 20, "ψ": 21, "e": 22, "ζ": 23, "ό": 25, "ρ": 26, "β": 27, "α": 28, "ν": 29, "ϋ": 30, "v": 31, "ε": 32, "ά": 33, "g": 34, "ύ": 35, "κ": 36, "μ": 37, "έ": 38, "ς": 39, "ξ": 40, "ϊ": 41, "χ": 42, "o": 43, "ο": 44, "́": 45, "’": 46, "'": 47, "a": 48, "ω": 49, "υ": 50, "|": 24, "[UNK]": 51, "[PAD]": 52}
|