Training in progress, step 100
Browse files- config.json +56 -0
- logs/events.out.tfevents.1724831059.3840f8e7e23d.918.0 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ammarnasr/t5mimo-seq2seq-conv",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5MIMOForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "ammarnasr/t5mimo-seq2seq-conv--configuration_t5mimo.T5MIMOConfig",
|
| 8 |
+
"AutoModel": "ammarnasr/t5mimo-seq2seq-conv--modeling_t5mimo.T5MIMOModel",
|
| 9 |
+
"AutoModelForSeq2SeqLM": "ammarnasr/t5mimo-seq2seq-conv--modeling_t5mimo.T5MIMOForConditionalGeneration"
|
| 10 |
+
},
|
| 11 |
+
"chronos_config": {
|
| 12 |
+
"context_length": 512,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"model_type": "seq2seq",
|
| 15 |
+
"n_special_tokens": 2,
|
| 16 |
+
"n_tokens": 4096,
|
| 17 |
+
"num_samples": 20,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"prediction_length": 64,
|
| 20 |
+
"temperature": 1.0,
|
| 21 |
+
"tokenizer_class": "MeanScaleUniformBins",
|
| 22 |
+
"tokenizer_kwargs": {
|
| 23 |
+
"high_limit": 15,
|
| 24 |
+
"low_limit": -15
|
| 25 |
+
},
|
| 26 |
+
"top_k": 50,
|
| 27 |
+
"top_p": 1.0,
|
| 28 |
+
"use_eos_token": true
|
| 29 |
+
},
|
| 30 |
+
"classifier_dropout": 0.0,
|
| 31 |
+
"d_ff": 1024,
|
| 32 |
+
"d_kv": 64,
|
| 33 |
+
"d_model": 256,
|
| 34 |
+
"decoder_start_token_id": 0,
|
| 35 |
+
"dense_act_fn": "relu",
|
| 36 |
+
"dropout_rate": 0.1,
|
| 37 |
+
"eos_token_id": 1,
|
| 38 |
+
"feed_forward_proj": "relu",
|
| 39 |
+
"initializer_factor": 0.05,
|
| 40 |
+
"is_encoder_decoder": true,
|
| 41 |
+
"is_gated_act": false,
|
| 42 |
+
"layer_norm_epsilon": 1e-06,
|
| 43 |
+
"model_type": "t5mimo",
|
| 44 |
+
"num_decoder_layers": 4,
|
| 45 |
+
"num_filters": 64,
|
| 46 |
+
"num_heads": 4,
|
| 47 |
+
"num_layers": 4,
|
| 48 |
+
"num_seqs": 3,
|
| 49 |
+
"pad_token_id": 0,
|
| 50 |
+
"relative_attention_max_distance": 128,
|
| 51 |
+
"relative_attention_num_buckets": 32,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.42.4",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"vocab_size": 4096
|
| 56 |
+
}
|
logs/events.out.tfevents.1724831059.3840f8e7e23d.918.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6763b2f1f8278003c43f2228896e88040af878a8c27cf5d87962536abe72bc2
|
| 3 |
+
size 9823
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:245f53acb956ae005c72a0b6554649a47afdb8168fabc3a3b60cbe9f065b80c5
|
| 3 |
+
size 33649068
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1be1cba4a3c7fa906846755163f7b629086a1341f35753d5bb319ffcaacdb7ac
|
| 3 |
+
size 5112
|