Upload 8 files
Browse files- config.json +82 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +11 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +761 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_act": "relu",
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": false,
|
8 |
+
"apply_spec_augment": false,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2BertForAudioFrameClassification"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 768,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"conformer_conv_dropout": 0.1,
|
17 |
+
"contrastive_logits_temperature": 0.1,
|
18 |
+
"conv_depthwise_kernel_size": 31,
|
19 |
+
"ctc_loss_reduction": "sum",
|
20 |
+
"ctc_zero_infinity": false,
|
21 |
+
"diversity_loss_weight": 0.1,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.0,
|
24 |
+
"feat_quantizer_dropout": 0.0,
|
25 |
+
"feature_projection_input_dim": 160,
|
26 |
+
"final_dropout": 0.1,
|
27 |
+
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.0,
|
29 |
+
"hidden_size": 1024,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 4096,
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"layerdrop": 0.1,
|
34 |
+
"left_max_position_embeddings": 64,
|
35 |
+
"mask_feature_length": 10,
|
36 |
+
"mask_feature_min_masks": 0,
|
37 |
+
"mask_feature_prob": 0.0,
|
38 |
+
"mask_time_length": 10,
|
39 |
+
"mask_time_min_masks": 2,
|
40 |
+
"mask_time_prob": 0.05,
|
41 |
+
"max_source_positions": 5000,
|
42 |
+
"model_type": "wav2vec2-bert",
|
43 |
+
"num_adapter_layers": 1,
|
44 |
+
"num_attention_heads": 16,
|
45 |
+
"num_codevector_groups": 2,
|
46 |
+
"num_codevectors_per_group": 320,
|
47 |
+
"num_hidden_layers": 24,
|
48 |
+
"num_negatives": 100,
|
49 |
+
"output_hidden_size": 1024,
|
50 |
+
"pad_token_id": 0,
|
51 |
+
"position_embeddings_type": "relative_key",
|
52 |
+
"proj_codevector_dim": 768,
|
53 |
+
"right_max_position_embeddings": 8,
|
54 |
+
"rotary_embedding_base": 10000,
|
55 |
+
"tdnn_dilation": [
|
56 |
+
1,
|
57 |
+
2,
|
58 |
+
3,
|
59 |
+
1,
|
60 |
+
1
|
61 |
+
],
|
62 |
+
"tdnn_dim": [
|
63 |
+
512,
|
64 |
+
512,
|
65 |
+
512,
|
66 |
+
512,
|
67 |
+
1500
|
68 |
+
],
|
69 |
+
"tdnn_kernel": [
|
70 |
+
5,
|
71 |
+
3,
|
72 |
+
3,
|
73 |
+
1,
|
74 |
+
1
|
75 |
+
],
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.43.4",
|
78 |
+
"use_intermediate_ffn_before_adapter": false,
|
79 |
+
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": null,
|
81 |
+
"xvector_output_dim": 512
|
82 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43583a5f45a1491e37214b4e389812a0c3f4386434540967f727347e0f3380f1
|
3 |
+
size 2322082904
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a0bb21ae73964a78ec4ab4d477c261432d2adaddbd8e38a0777d07a714cdbe
|
3 |
+
size 4644605544
|
preprocessor_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
|
3 |
+
"feature_size": 80,
|
4 |
+
"num_mel_bins": 80,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 1,
|
7 |
+
"processor_class": "Wav2Vec2BertProcessor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000,
|
10 |
+
"stride": 2
|
11 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e5826593cc14eafca7f53068ca6561779ee8155f447fed54e720df5f8aa5cf
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01d48e83168dc87f99a5f312797e4ceac5456bd3bbb6a6373d9d8cc4ac270cdc
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,761 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 19.71563981042654,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1040,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1895734597156398,
|
13 |
+
"grad_norm": 0.597112774848938,
|
14 |
+
"learning_rate": 2.9711538461538464e-05,
|
15 |
+
"loss": 0.435,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3791469194312796,
|
20 |
+
"grad_norm": 0.16265545785427094,
|
21 |
+
"learning_rate": 2.9423076923076923e-05,
|
22 |
+
"loss": 0.1842,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5687203791469194,
|
27 |
+
"grad_norm": 0.13190606236457825,
|
28 |
+
"learning_rate": 2.9134615384615386e-05,
|
29 |
+
"loss": 0.1818,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.7582938388625592,
|
34 |
+
"grad_norm": 0.1712672859430313,
|
35 |
+
"learning_rate": 2.884615384615385e-05,
|
36 |
+
"loss": 0.1685,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.9478672985781991,
|
41 |
+
"grad_norm": 0.17000597715377808,
|
42 |
+
"learning_rate": 2.855769230769231e-05,
|
43 |
+
"loss": 0.1694,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.1374407582938388,
|
48 |
+
"grad_norm": 0.04239616543054581,
|
49 |
+
"learning_rate": 2.8269230769230768e-05,
|
50 |
+
"loss": 0.1564,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.3270142180094786,
|
55 |
+
"grad_norm": 0.055856816470623016,
|
56 |
+
"learning_rate": 2.798076923076923e-05,
|
57 |
+
"loss": 0.1675,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.5165876777251186,
|
62 |
+
"grad_norm": 0.05924641340970993,
|
63 |
+
"learning_rate": 2.7692307692307694e-05,
|
64 |
+
"loss": 0.1751,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.7061611374407581,
|
69 |
+
"grad_norm": 0.04663912579417229,
|
70 |
+
"learning_rate": 2.7403846153846153e-05,
|
71 |
+
"loss": 0.1598,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.8957345971563981,
|
76 |
+
"grad_norm": 0.07988695800304413,
|
77 |
+
"learning_rate": 2.7115384615384616e-05,
|
78 |
+
"loss": 0.1489,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.085308056872038,
|
83 |
+
"grad_norm": 0.1717785745859146,
|
84 |
+
"learning_rate": 2.682692307692308e-05,
|
85 |
+
"loss": 0.1668,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.2748815165876777,
|
90 |
+
"grad_norm": 0.15836206078529358,
|
91 |
+
"learning_rate": 2.6538461538461538e-05,
|
92 |
+
"loss": 0.1543,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.4644549763033177,
|
97 |
+
"grad_norm": 0.023397250100970268,
|
98 |
+
"learning_rate": 2.625e-05,
|
99 |
+
"loss": 0.1686,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.654028436018957,
|
104 |
+
"grad_norm": 0.2287532091140747,
|
105 |
+
"learning_rate": 2.5961538461538464e-05,
|
106 |
+
"loss": 0.1645,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.843601895734597,
|
111 |
+
"grad_norm": 0.3427872061729431,
|
112 |
+
"learning_rate": 2.5673076923076923e-05,
|
113 |
+
"loss": 0.133,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.0331753554502368,
|
118 |
+
"grad_norm": 0.307771772146225,
|
119 |
+
"learning_rate": 2.5384615384615386e-05,
|
120 |
+
"loss": 0.103,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.2227488151658767,
|
125 |
+
"grad_norm": 0.30710339546203613,
|
126 |
+
"learning_rate": 2.509615384615385e-05,
|
127 |
+
"loss": 0.0924,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.4123222748815167,
|
132 |
+
"grad_norm": 0.20707634091377258,
|
133 |
+
"learning_rate": 2.4807692307692305e-05,
|
134 |
+
"loss": 0.0749,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.6018957345971563,
|
139 |
+
"grad_norm": 0.2535831034183502,
|
140 |
+
"learning_rate": 2.4519230769230768e-05,
|
141 |
+
"loss": 0.0704,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 3.7914691943127963,
|
146 |
+
"grad_norm": 0.2260940968990326,
|
147 |
+
"learning_rate": 2.423076923076923e-05,
|
148 |
+
"loss": 0.0688,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 3.9810426540284363,
|
153 |
+
"grad_norm": 0.21390962600708008,
|
154 |
+
"learning_rate": 2.3942307692307694e-05,
|
155 |
+
"loss": 0.0585,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.170616113744076,
|
160 |
+
"grad_norm": 0.1833769828081131,
|
161 |
+
"learning_rate": 2.3653846153846153e-05,
|
162 |
+
"loss": 0.054,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 4.360189573459715,
|
167 |
+
"grad_norm": 0.2922685146331787,
|
168 |
+
"learning_rate": 2.3365384615384616e-05,
|
169 |
+
"loss": 0.0538,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.549763033175355,
|
174 |
+
"grad_norm": 0.2239004522562027,
|
175 |
+
"learning_rate": 2.307692307692308e-05,
|
176 |
+
"loss": 0.0543,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 4.739336492890995,
|
181 |
+
"grad_norm": 0.17778703570365906,
|
182 |
+
"learning_rate": 2.278846153846154e-05,
|
183 |
+
"loss": 0.0561,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 4.928909952606635,
|
188 |
+
"grad_norm": 0.3559529483318329,
|
189 |
+
"learning_rate": 2.25e-05,
|
190 |
+
"loss": 0.0493,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.118483412322275,
|
195 |
+
"grad_norm": 0.12670384347438812,
|
196 |
+
"learning_rate": 2.2211538461538464e-05,
|
197 |
+
"loss": 0.049,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.308056872037914,
|
202 |
+
"grad_norm": 0.19230520725250244,
|
203 |
+
"learning_rate": 2.1923076923076924e-05,
|
204 |
+
"loss": 0.0477,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 5.497630331753554,
|
209 |
+
"grad_norm": 0.17324426770210266,
|
210 |
+
"learning_rate": 2.1634615384615383e-05,
|
211 |
+
"loss": 0.0434,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 5.687203791469194,
|
216 |
+
"grad_norm": 0.310581237077713,
|
217 |
+
"learning_rate": 2.1346153846153846e-05,
|
218 |
+
"loss": 0.0437,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 5.876777251184834,
|
223 |
+
"grad_norm": 0.14988450706005096,
|
224 |
+
"learning_rate": 2.1057692307692306e-05,
|
225 |
+
"loss": 0.0401,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 6.0663507109004735,
|
230 |
+
"grad_norm": 0.1281799077987671,
|
231 |
+
"learning_rate": 2.076923076923077e-05,
|
232 |
+
"loss": 0.0397,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 6.2559241706161135,
|
237 |
+
"grad_norm": 0.1899699568748474,
|
238 |
+
"learning_rate": 2.048076923076923e-05,
|
239 |
+
"loss": 0.0399,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 6.4454976303317535,
|
244 |
+
"grad_norm": 0.14849646389484406,
|
245 |
+
"learning_rate": 2.0192307692307694e-05,
|
246 |
+
"loss": 0.0394,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 6.6350710900473935,
|
251 |
+
"grad_norm": 0.1111103966832161,
|
252 |
+
"learning_rate": 1.9903846153846154e-05,
|
253 |
+
"loss": 0.0361,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 6.8246445497630335,
|
258 |
+
"grad_norm": 0.1525595635175705,
|
259 |
+
"learning_rate": 1.9615384615384617e-05,
|
260 |
+
"loss": 0.039,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.014218009478673,
|
265 |
+
"grad_norm": 0.2204810231924057,
|
266 |
+
"learning_rate": 1.932692307692308e-05,
|
267 |
+
"loss": 0.0374,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.203791469194313,
|
272 |
+
"grad_norm": 0.1169096827507019,
|
273 |
+
"learning_rate": 1.903846153846154e-05,
|
274 |
+
"loss": 0.0339,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 7.393364928909953,
|
279 |
+
"grad_norm": 0.09804651141166687,
|
280 |
+
"learning_rate": 1.8750000000000002e-05,
|
281 |
+
"loss": 0.0359,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 7.5829383886255926,
|
286 |
+
"grad_norm": 0.14222651720046997,
|
287 |
+
"learning_rate": 1.8461538461538465e-05,
|
288 |
+
"loss": 0.0321,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 7.7725118483412325,
|
293 |
+
"grad_norm": 0.0966310054063797,
|
294 |
+
"learning_rate": 1.817307692307692e-05,
|
295 |
+
"loss": 0.0327,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 7.9620853080568725,
|
300 |
+
"grad_norm": 0.11295436322689056,
|
301 |
+
"learning_rate": 1.7884615384615384e-05,
|
302 |
+
"loss": 0.0359,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 8.151658767772512,
|
307 |
+
"grad_norm": 0.09200425446033478,
|
308 |
+
"learning_rate": 1.7596153846153846e-05,
|
309 |
+
"loss": 0.0333,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 8.341232227488153,
|
314 |
+
"grad_norm": 0.08960484713315964,
|
315 |
+
"learning_rate": 1.7307692307692306e-05,
|
316 |
+
"loss": 0.03,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 8.530805687203792,
|
321 |
+
"grad_norm": 0.1008763536810875,
|
322 |
+
"learning_rate": 1.701923076923077e-05,
|
323 |
+
"loss": 0.0328,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 8.72037914691943,
|
328 |
+
"grad_norm": 0.18892982602119446,
|
329 |
+
"learning_rate": 1.673076923076923e-05,
|
330 |
+
"loss": 0.0316,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 8.909952606635072,
|
335 |
+
"grad_norm": 0.16451339423656464,
|
336 |
+
"learning_rate": 1.6442307692307695e-05,
|
337 |
+
"loss": 0.0301,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.09952606635071,
|
342 |
+
"grad_norm": 0.14853718876838684,
|
343 |
+
"learning_rate": 1.6153846153846154e-05,
|
344 |
+
"loss": 0.0302,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 9.289099526066352,
|
349 |
+
"grad_norm": 0.0903206467628479,
|
350 |
+
"learning_rate": 1.5865384615384617e-05,
|
351 |
+
"loss": 0.0314,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 9.47867298578199,
|
356 |
+
"grad_norm": 0.16619105637073517,
|
357 |
+
"learning_rate": 1.557692307692308e-05,
|
358 |
+
"loss": 0.0278,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 9.66824644549763,
|
363 |
+
"grad_norm": 0.11136868596076965,
|
364 |
+
"learning_rate": 1.528846153846154e-05,
|
365 |
+
"loss": 0.0303,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 9.85781990521327,
|
370 |
+
"grad_norm": 0.09969611465930939,
|
371 |
+
"learning_rate": 1.5e-05,
|
372 |
+
"loss": 0.0299,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 10.04739336492891,
|
377 |
+
"grad_norm": 0.09576759487390518,
|
378 |
+
"learning_rate": 1.4711538461538462e-05,
|
379 |
+
"loss": 0.0278,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 10.23696682464455,
|
384 |
+
"grad_norm": 0.1151731088757515,
|
385 |
+
"learning_rate": 1.4423076923076924e-05,
|
386 |
+
"loss": 0.0269,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 10.42654028436019,
|
391 |
+
"grad_norm": 0.2266397476196289,
|
392 |
+
"learning_rate": 1.4134615384615384e-05,
|
393 |
+
"loss": 0.0289,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 10.616113744075829,
|
398 |
+
"grad_norm": 0.12434451282024384,
|
399 |
+
"learning_rate": 1.3846153846153847e-05,
|
400 |
+
"loss": 0.0261,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 10.80568720379147,
|
405 |
+
"grad_norm": 0.1091102734208107,
|
406 |
+
"learning_rate": 1.3557692307692308e-05,
|
407 |
+
"loss": 0.028,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 10.995260663507109,
|
412 |
+
"grad_norm": 0.08422732353210449,
|
413 |
+
"learning_rate": 1.3269230769230769e-05,
|
414 |
+
"loss": 0.0256,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 11.184834123222748,
|
419 |
+
"grad_norm": 0.16355375945568085,
|
420 |
+
"learning_rate": 1.2980769230769232e-05,
|
421 |
+
"loss": 0.0269,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 11.374407582938389,
|
426 |
+
"grad_norm": 0.26286429166793823,
|
427 |
+
"learning_rate": 1.2692307692307693e-05,
|
428 |
+
"loss": 0.0239,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 11.563981042654028,
|
433 |
+
"grad_norm": 0.0981736034154892,
|
434 |
+
"learning_rate": 1.2403846153846153e-05,
|
435 |
+
"loss": 0.0291,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 11.753554502369669,
|
440 |
+
"grad_norm": 0.11100564897060394,
|
441 |
+
"learning_rate": 1.2115384615384615e-05,
|
442 |
+
"loss": 0.0251,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 11.943127962085308,
|
447 |
+
"grad_norm": 0.07715968787670135,
|
448 |
+
"learning_rate": 1.1826923076923077e-05,
|
449 |
+
"loss": 0.0266,
|
450 |
+
"step": 630
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 12.132701421800947,
|
454 |
+
"grad_norm": 0.12548160552978516,
|
455 |
+
"learning_rate": 1.153846153846154e-05,
|
456 |
+
"loss": 0.0232,
|
457 |
+
"step": 640
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 12.322274881516588,
|
461 |
+
"grad_norm": 0.11867664009332657,
|
462 |
+
"learning_rate": 1.125e-05,
|
463 |
+
"loss": 0.0239,
|
464 |
+
"step": 650
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 12.511848341232227,
|
468 |
+
"grad_norm": 0.124052494764328,
|
469 |
+
"learning_rate": 1.0961538461538462e-05,
|
470 |
+
"loss": 0.0258,
|
471 |
+
"step": 660
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 12.701421800947868,
|
475 |
+
"grad_norm": 0.45495718717575073,
|
476 |
+
"learning_rate": 1.0673076923076923e-05,
|
477 |
+
"loss": 0.0242,
|
478 |
+
"step": 670
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 12.890995260663507,
|
482 |
+
"grad_norm": 0.0678386464715004,
|
483 |
+
"learning_rate": 1.0384615384615384e-05,
|
484 |
+
"loss": 0.0242,
|
485 |
+
"step": 680
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 13.080568720379146,
|
489 |
+
"grad_norm": 0.06402502954006195,
|
490 |
+
"learning_rate": 1.0096153846153847e-05,
|
491 |
+
"loss": 0.0253,
|
492 |
+
"step": 690
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 13.270142180094787,
|
496 |
+
"grad_norm": 0.10899492353200912,
|
497 |
+
"learning_rate": 9.807692307692308e-06,
|
498 |
+
"loss": 0.0234,
|
499 |
+
"step": 700
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 13.459715639810426,
|
503 |
+
"grad_norm": 0.09529020637273788,
|
504 |
+
"learning_rate": 9.51923076923077e-06,
|
505 |
+
"loss": 0.0227,
|
506 |
+
"step": 710
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 13.649289099526067,
|
510 |
+
"grad_norm": 0.10726472735404968,
|
511 |
+
"learning_rate": 9.230769230769232e-06,
|
512 |
+
"loss": 0.0226,
|
513 |
+
"step": 720
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 13.838862559241706,
|
517 |
+
"grad_norm": 0.05985069274902344,
|
518 |
+
"learning_rate": 8.942307692307692e-06,
|
519 |
+
"loss": 0.0211,
|
520 |
+
"step": 730
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 14.028436018957345,
|
524 |
+
"grad_norm": 0.12114176154136658,
|
525 |
+
"learning_rate": 8.653846153846153e-06,
|
526 |
+
"loss": 0.0245,
|
527 |
+
"step": 740
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 14.218009478672986,
|
531 |
+
"grad_norm": 0.11160324513912201,
|
532 |
+
"learning_rate": 8.365384615384616e-06,
|
533 |
+
"loss": 0.0196,
|
534 |
+
"step": 750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 14.407582938388625,
|
538 |
+
"grad_norm": 0.087327741086483,
|
539 |
+
"learning_rate": 8.076923076923077e-06,
|
540 |
+
"loss": 0.0193,
|
541 |
+
"step": 760
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 14.597156398104266,
|
545 |
+
"grad_norm": 0.06679825484752655,
|
546 |
+
"learning_rate": 7.78846153846154e-06,
|
547 |
+
"loss": 0.0206,
|
548 |
+
"step": 770
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 14.786729857819905,
|
552 |
+
"grad_norm": 0.14305196702480316,
|
553 |
+
"learning_rate": 7.5e-06,
|
554 |
+
"loss": 0.0194,
|
555 |
+
"step": 780
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 14.976303317535544,
|
559 |
+
"grad_norm": 0.11618325114250183,
|
560 |
+
"learning_rate": 7.211538461538462e-06,
|
561 |
+
"loss": 0.0257,
|
562 |
+
"step": 790
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 15.165876777251185,
|
566 |
+
"grad_norm": 0.06295182555913925,
|
567 |
+
"learning_rate": 6.923076923076923e-06,
|
568 |
+
"loss": 0.0184,
|
569 |
+
"step": 800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 15.355450236966824,
|
573 |
+
"grad_norm": 0.08175351470708847,
|
574 |
+
"learning_rate": 6.6346153846153846e-06,
|
575 |
+
"loss": 0.0209,
|
576 |
+
"step": 810
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 15.545023696682465,
|
580 |
+
"grad_norm": 0.11890088021755219,
|
581 |
+
"learning_rate": 6.3461538461538466e-06,
|
582 |
+
"loss": 0.0215,
|
583 |
+
"step": 820
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 15.734597156398104,
|
587 |
+
"grad_norm": 0.17722468078136444,
|
588 |
+
"learning_rate": 6.057692307692308e-06,
|
589 |
+
"loss": 0.0203,
|
590 |
+
"step": 830
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 15.924170616113743,
|
594 |
+
"grad_norm": 0.11907941102981567,
|
595 |
+
"learning_rate": 5.76923076923077e-06,
|
596 |
+
"loss": 0.021,
|
597 |
+
"step": 840
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 16.113744075829384,
|
601 |
+
"grad_norm": 0.1066436693072319,
|
602 |
+
"learning_rate": 5.480769230769231e-06,
|
603 |
+
"loss": 0.0218,
|
604 |
+
"step": 850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 16.303317535545023,
|
608 |
+
"grad_norm": 0.053932033479213715,
|
609 |
+
"learning_rate": 5.192307692307692e-06,
|
610 |
+
"loss": 0.0184,
|
611 |
+
"step": 860
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 16.492890995260662,
|
615 |
+
"grad_norm": 0.09704640507698059,
|
616 |
+
"learning_rate": 4.903846153846154e-06,
|
617 |
+
"loss": 0.0191,
|
618 |
+
"step": 870
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 16.682464454976305,
|
622 |
+
"grad_norm": 0.10457386821508408,
|
623 |
+
"learning_rate": 4.615384615384616e-06,
|
624 |
+
"loss": 0.0197,
|
625 |
+
"step": 880
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 16.872037914691944,
|
629 |
+
"grad_norm": 0.08160708844661713,
|
630 |
+
"learning_rate": 4.3269230769230765e-06,
|
631 |
+
"loss": 0.0204,
|
632 |
+
"step": 890
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 17.061611374407583,
|
636 |
+
"grad_norm": 0.1239229142665863,
|
637 |
+
"learning_rate": 4.0384615384615385e-06,
|
638 |
+
"loss": 0.0208,
|
639 |
+
"step": 900
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 17.251184834123222,
|
643 |
+
"grad_norm": 0.0887596532702446,
|
644 |
+
"learning_rate": 3.75e-06,
|
645 |
+
"loss": 0.017,
|
646 |
+
"step": 910
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 17.44075829383886,
|
650 |
+
"grad_norm": 0.09922682493925095,
|
651 |
+
"learning_rate": 3.4615384615384617e-06,
|
652 |
+
"loss": 0.0223,
|
653 |
+
"step": 920
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 17.6303317535545,
|
657 |
+
"grad_norm": 0.0974949300289154,
|
658 |
+
"learning_rate": 3.1730769230769233e-06,
|
659 |
+
"loss": 0.0191,
|
660 |
+
"step": 930
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 17.819905213270143,
|
664 |
+
"grad_norm": 0.10244361311197281,
|
665 |
+
"learning_rate": 2.884615384615385e-06,
|
666 |
+
"loss": 0.0198,
|
667 |
+
"step": 940
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 18.009478672985782,
|
671 |
+
"grad_norm": 0.06859322637319565,
|
672 |
+
"learning_rate": 2.596153846153846e-06,
|
673 |
+
"loss": 0.0188,
|
674 |
+
"step": 950
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 18.19905213270142,
|
678 |
+
"grad_norm": 0.09902096539735794,
|
679 |
+
"learning_rate": 2.307692307692308e-06,
|
680 |
+
"loss": 0.0196,
|
681 |
+
"step": 960
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 18.38862559241706,
|
685 |
+
"grad_norm": 0.058132074773311615,
|
686 |
+
"learning_rate": 2.0192307692307692e-06,
|
687 |
+
"loss": 0.0174,
|
688 |
+
"step": 970
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 18.578199052132703,
|
692 |
+
"grad_norm": 0.11522402614355087,
|
693 |
+
"learning_rate": 1.7307692307692308e-06,
|
694 |
+
"loss": 0.0186,
|
695 |
+
"step": 980
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 18.767772511848342,
|
699 |
+
"grad_norm": 0.07329108566045761,
|
700 |
+
"learning_rate": 1.4423076923076924e-06,
|
701 |
+
"loss": 0.0203,
|
702 |
+
"step": 990
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 18.95734597156398,
|
706 |
+
"grad_norm": 0.08888276666402817,
|
707 |
+
"learning_rate": 1.153846153846154e-06,
|
708 |
+
"loss": 0.0182,
|
709 |
+
"step": 1000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 19.14691943127962,
|
713 |
+
"grad_norm": 0.16812676191329956,
|
714 |
+
"learning_rate": 8.653846153846154e-07,
|
715 |
+
"loss": 0.0201,
|
716 |
+
"step": 1010
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 19.33649289099526,
|
720 |
+
"grad_norm": 0.051739402115345,
|
721 |
+
"learning_rate": 5.76923076923077e-07,
|
722 |
+
"loss": 0.0175,
|
723 |
+
"step": 1020
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 19.5260663507109,
|
727 |
+
"grad_norm": 0.15502548217773438,
|
728 |
+
"learning_rate": 2.884615384615385e-07,
|
729 |
+
"loss": 0.0211,
|
730 |
+
"step": 1030
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 19.71563981042654,
|
734 |
+
"grad_norm": 0.10121985524892807,
|
735 |
+
"learning_rate": 0.0,
|
736 |
+
"loss": 0.0202,
|
737 |
+
"step": 1040
|
738 |
+
}
|
739 |
+
],
|
740 |
+
"logging_steps": 10,
|
741 |
+
"max_steps": 1040,
|
742 |
+
"num_input_tokens_seen": 0,
|
743 |
+
"num_train_epochs": 20,
|
744 |
+
"save_steps": 500,
|
745 |
+
"stateful_callbacks": {
|
746 |
+
"TrainerControl": {
|
747 |
+
"args": {
|
748 |
+
"should_epoch_stop": false,
|
749 |
+
"should_evaluate": false,
|
750 |
+
"should_log": false,
|
751 |
+
"should_save": true,
|
752 |
+
"should_training_stop": true
|
753 |
+
},
|
754 |
+
"attributes": {}
|
755 |
+
}
|
756 |
+
},
|
757 |
+
"total_flos": 1.39069062991872e+19,
|
758 |
+
"train_batch_size": 1,
|
759 |
+
"trial_name": null,
|
760 |
+
"trial_params": null
|
761 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdd7dedd848e450132fc25e3103d48e098bf3d20f0518bc38900701105824cfd
|
3 |
+
size 5176
|