Model save
Browse files- adapter_config.json +5 -5
- all_results.json +3 -3
- config.json +28 -0
- train_results.json +3 -3
- trainer_state.json +3 -3
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -19,13 +19,13 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"q_proj",
|
| 23 |
-
"k_proj",
|
| 24 |
"o_proj",
|
| 25 |
-
"up_proj",
|
| 26 |
"gate_proj",
|
| 27 |
-
"
|
| 28 |
-
"
|
|
|
|
|
|
|
|
|
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
|
|
|
| 22 |
"o_proj",
|
|
|
|
| 23 |
"gate_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"train_loss": 6.198014577229817,
|
| 4 |
-
"train_runtime": 11.
|
| 5 |
"train_samples": 6321,
|
| 6 |
-
"train_samples_per_second": 1.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"train_loss": 6.198014577229817,
|
| 4 |
+
"train_runtime": 11.6256,
|
| 5 |
"train_samples": 6321,
|
| 6 |
+
"train_samples_per_second": 1.032,
|
| 7 |
+
"train_steps_per_second": 0.258
|
| 8 |
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.34.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 128256
|
| 28 |
+
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"train_loss": 6.198014577229817,
|
| 4 |
-
"train_runtime": 11.
|
| 5 |
"train_samples": 6321,
|
| 6 |
-
"train_samples_per_second": 1.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
"train_loss": 6.198014577229817,
|
| 4 |
+
"train_runtime": 11.6256,
|
| 5 |
"train_samples": 6321,
|
| 6 |
+
"train_samples_per_second": 1.032,
|
| 7 |
+
"train_steps_per_second": 0.258
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -19,9 +19,9 @@
|
|
| 19 |
"step": 3,
|
| 20 |
"total_flos": 4717082050560.0,
|
| 21 |
"train_loss": 6.198014577229817,
|
| 22 |
-
"train_runtime": 11.
|
| 23 |
-
"train_samples_per_second": 1.
|
| 24 |
-
"train_steps_per_second": 0.
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 5,
|
|
|
|
| 19 |
"step": 3,
|
| 20 |
"total_flos": 4717082050560.0,
|
| 21 |
"train_loss": 6.198014577229817,
|
| 22 |
+
"train_runtime": 11.6256,
|
| 23 |
+
"train_samples_per_second": 1.032,
|
| 24 |
+
"train_steps_per_second": 0.258
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 5,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4568e2722756d3994f84ab45d155eca91e7b85f068723f9f6a6b34a61738aa73
|
| 3 |
size 5688
|