Upload ./ with huggingface_hub
Browse files- config.json +32 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +22 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "MBZUAI/LaMini-Cerebras-256M",
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_embd": 1088,
|
| 15 |
+
"n_head": 17,
|
| 16 |
+
"n_inner": 4352,
|
| 17 |
+
"n_layer": 14,
|
| 18 |
+
"n_positions": 2048,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.0,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.20.1",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 50258
|
| 32 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b54d989a4a8faf8981f3b5526f06922b17e1aa91700e5972985d5ee78ac0bcaa
|
| 3 |
+
size 2047924433
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaf14e1e757cb1d60da39cb59e0da74b36f7f91a2a05192b0ea74ee947706c16
|
| 3 |
+
size 1082695985
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff0b7d688f72cecc3d6db8a5558dfafab2669c75076ea7f5e8d0318cba901963
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:333aa67bbfa3d53e95567957a613686a6f42192e77864ec20f1895020f36b1cf
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.561304836895388,
|
| 5 |
+
"global_step": 8500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 5.62,
|
| 12 |
+
"learning_rate": 4.380630630630631e-05,
|
| 13 |
+
"loss": 0.5361,
|
| 14 |
+
"step": 5000
|
| 15 |
+
}
|
| 16 |
+
],
|
| 17 |
+
"max_steps": 8890,
|
| 18 |
+
"num_train_epochs": 10,
|
| 19 |
+
"total_flos": 1.2465519921620582e+17,
|
| 20 |
+
"trial_name": null,
|
| 21 |
+
"trial_params": null
|
| 22 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddcd70c8b942d36eb0abdef0fabc5743b97856f08054e2b9e34a1dc0e2695d92
|
| 3 |
+
size 3247
|