Training in progress, step 10
Browse files
adapter_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"alpha_pattern": {},
|
| 4 |
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
-
"base_model_name_or_path": "meta-llama/Llama-3.
|
| 7 |
"bias": "none",
|
| 8 |
"corda_config": null,
|
| 9 |
"ensure_weight_tying": false,
|
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"down_proj",
|
| 33 |
-
"gate_proj",
|
| 34 |
"v_proj",
|
|
|
|
|
|
|
| 35 |
"k_proj",
|
| 36 |
"up_proj",
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 3 |
"alpha_pattern": {},
|
| 4 |
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
| 7 |
"bias": "none",
|
| 8 |
"corda_config": null,
|
| 9 |
"ensure_weight_tying": false,
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
|
|
|
|
|
|
| 32 |
"v_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
"k_proj",
|
| 36 |
"up_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
+
"gate_proj"
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6760d31fbf3d5a6343036b485d27a3a76c64b35026af34d485c514d2435acb38
|
| 3 |
+
size 194563400
|
runs/Dec17_09-52-46_c45610aa664c/events.out.tfevents.1765965171.c45610aa664c.1078.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a2aebad239b7de0ff9579e6aecca463feb26704fc70425cc0422166e785ab0
|
| 3 |
+
size 6251
|
special_tokens_map.json
CHANGED
|
@@ -7,11 +7,11 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "<|
|
| 17 |
}
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<|end_of_text|>"
|
| 17 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2051,13 +2051,13 @@
|
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
-
"eos_token": "<|
|
| 2055 |
"extra_special_tokens": {},
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
-
"pad_token": "<|
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
}
|
|
|
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
+
"eos_token": "<|end_of_text|>",
|
| 2055 |
"extra_special_tokens": {},
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|end_of_text|>",
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6097
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b9ff7fd9432f2963474cfa9bf43b7ada94fb55ffb84095a19d5f167ecd5fd0a
|
| 3 |
size 6097
|