Training in progress, epoch 0, checkpoint
Browse files- checkpoint-2518560/config.json +28 -0
- checkpoint-2518560/generation_config.json +7 -0
- checkpoint-2518560/optimizer.pt +3 -0
- checkpoint-2518560/pytorch_model.bin +3 -0
- checkpoint-2518560/rng_state.pth +3 -0
- checkpoint-2518560/scheduler.pt +3 -0
- checkpoint-2518560/special_tokens_map.json +5 -0
- checkpoint-2518560/tokenizer.json +0 -0
- checkpoint-2518560/tokenizer_config.json +12 -0
- checkpoint-2518560/trainer_state.json +0 -0
- checkpoint-2518560/training_args.bin +3 -0
checkpoint-2518560/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_remove_final_layer_norm": false,
|
3 |
+
"activation_function": "relu",
|
4 |
+
"architectures": [
|
5 |
+
"OPTForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"do_layer_norm_before": true,
|
10 |
+
"dropout": 0.1,
|
11 |
+
"enable_bias": true,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"ffn_dim": 768,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"init_std": 0.02,
|
16 |
+
"layer_norm_elementwise_affine": true,
|
17 |
+
"layerdrop": 0.0,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "opt",
|
20 |
+
"num_attention_heads": 8,
|
21 |
+
"num_hidden_layers": 8,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.33.3",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50002,
|
27 |
+
"word_embed_proj_dim": 768
|
28 |
+
}
|
checkpoint-2518560/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": "4.33.3"
|
7 |
+
}
|
checkpoint-2518560/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccaf6b1e035081af942e0f41363a7c3eb0e828bda0191ca4cdfffb87d87c03e1
|
3 |
+
size 537476677
|
checkpoint-2518560/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2613db23c749548f67c6e6e267ea7633b62b4b37cf21bb58b0a324611c0761d9
|
3 |
+
size 268727709
|
checkpoint-2518560/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6587b7cf9cd1ae09258b3966a3996b84700f32b91020f88bb3dca3569dfa11e
|
3 |
+
size 14575
|
checkpoint-2518560/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1948cd42f82dfaa7c1f21f6ca4f0920b1aac18bedb0a789399f42441c462ff2
|
3 |
+
size 627
|
checkpoint-2518560/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<eos>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-2518560/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2518560/tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"max_length": null,
|
5 |
+
"model_max_length": 512,
|
6 |
+
"pad_to_multiple_of": null,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"pad_token_type_id": 0,
|
9 |
+
"padding_side": "right",
|
10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
checkpoint-2518560/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2518560/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e75e2e85faac946b82c52de519dbf20642d527f656aa4d42d6128dd620bb1793
|
3 |
+
size 4283
|