Upload ./ with huggingface_hub
Browse files- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +28 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/pythia-1b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"model_type": "gpt_neox",
|
| 17 |
+
"num_attention_heads": 8,
|
| 18 |
+
"num_hidden_layers": 16,
|
| 19 |
+
"rotary_emb_base": 10000,
|
| 20 |
+
"rotary_pct": 0.25,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.20.1",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"use_parallel_residual": true,
|
| 26 |
+
"vocab_size": 50277
|
| 27 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1cb795fe9c1c8b85e8fcb32a3958fee9a262b6bb50c04938cf6d0962b15e9d6
|
| 3 |
+
size 8093484053
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42788bcca41d6c43fb8f727fc58718a0bb5c34afe889b7a24f98c7f3af04962a
|
| 3 |
+
size 4113875225
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69a15e581e7afd6fd12d6dddef3da31e19b3dd058003b5c5d00781b54e093f7c
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b571aebad525d52947931916cdefa151b1036b8ce309e76190d3f736c59d7466
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.878048780487805,
|
| 5 |
+
"global_step": 13000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.88,
|
| 12 |
+
"learning_rate": 8.126876876876877e-05,
|
| 13 |
+
"loss": 0.7477,
|
| 14 |
+
"step": 5000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 3.75,
|
| 18 |
+
"learning_rate": 6.25e-05,
|
| 19 |
+
"loss": 0.3572,
|
| 20 |
+
"step": 10000
|
| 21 |
+
}
|
| 22 |
+
],
|
| 23 |
+
"max_steps": 26650,
|
| 24 |
+
"num_train_epochs": 10,
|
| 25 |
+
"total_flos": 2.9029760945985946e+17,
|
| 26 |
+
"trial_name": null,
|
| 27 |
+
"trial_params": null
|
| 28 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f88ee1b6f7c076251f447c30b07942b1afdf5cbd106c7801af470e8017054d5
|
| 3 |
+
size 3247
|