Model save
Browse files- README.md +2 -7
- all_results.json +4 -4
- config.json +1 -1
- runs/Sep24_11-39-07_COE-CS-sv003/events.out.tfevents.1727178370.COE-CS-sv003.781675.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +5 -5
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,15 +3,10 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
5 |
tags:
|
6 |
-
- alignment-handbook
|
7 |
-
- trl
|
8 |
-
- sft
|
9 |
-
- generated_from_trainer
|
10 |
- trl
|
11 |
- sft
|
|
|
12 |
- generated_from_trainer
|
13 |
-
datasets:
|
14 |
-
- preference-data
|
15 |
model-index:
|
16 |
- name: preference_p0.1_seed42_level2_syntaxmixbatch16
|
17 |
results: []
|
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
22 |
|
23 |
# preference_p0.1_seed42_level2_syntaxmixbatch16
|
24 |
|
25 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
5 |
tags:
|
|
|
|
|
|
|
|
|
6 |
- trl
|
7 |
- sft
|
8 |
+
- alignment-handbook
|
9 |
- generated_from_trainer
|
|
|
|
|
10 |
model-index:
|
11 |
- name: preference_p0.1_seed42_level2_syntaxmixbatch16
|
12 |
results: []
|
|
|
17 |
|
18 |
# preference_p0.1_seed42_level2_syntaxmixbatch16
|
19 |
|
20 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
CHANGED
@@ -5,9 +5,9 @@
|
|
5 |
"eval_samples_per_second": 3.076,
|
6 |
"eval_steps_per_second": 0.923,
|
7 |
"total_flos": 252302485094400.0,
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 98873,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second":
|
13 |
}
|
|
|
5 |
"eval_samples_per_second": 3.076,
|
6 |
"eval_steps_per_second": 0.923,
|
7 |
"total_flos": 252302485094400.0,
|
8 |
+
"train_loss": 0.0,
|
9 |
+
"train_runtime": 0.0091,
|
10 |
"train_samples": 98873,
|
11 |
+
"train_samples_per_second": 4252334.509,
|
12 |
+
"train_steps_per_second": 265770.907
|
13 |
}
|
config.json
CHANGED
@@ -22,6 +22,6 @@
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.2",
|
25 |
-
"use_cache":
|
26 |
"vocab_size": 32000
|
27 |
}
|
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.2",
|
25 |
+
"use_cache": false,
|
26 |
"vocab_size": 32000
|
27 |
}
|
runs/Sep24_11-39-07_COE-CS-sv003/events.out.tfevents.1727178370.COE-CS-sv003.781675.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06fa62e995a7265cfdbd6bbd2cdd67b87657fab057e1d6aaff04c992e993668a
|
3 |
+
size 5628
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 252302485094400.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 98873,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 252302485094400.0,
|
4 |
+
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.0091,
|
6 |
"train_samples": 98873,
|
7 |
+
"train_samples_per_second": 4252334.509,
|
8 |
+
"train_steps_per_second": 265770.907
|
9 |
}
|
trainer_state.json
CHANGED
@@ -3400,14 +3400,14 @@
|
|
3400 |
"epoch": 1.0,
|
3401 |
"step": 2410,
|
3402 |
"total_flos": 252302485094400.0,
|
3403 |
-
"train_loss": 0.
|
3404 |
-
"train_runtime":
|
3405 |
-
"train_samples_per_second":
|
3406 |
-
"train_steps_per_second":
|
3407 |
}
|
3408 |
],
|
3409 |
"logging_steps": 5,
|
3410 |
-
"max_steps":
|
3411 |
"num_input_tokens_seen": 0,
|
3412 |
"num_train_epochs": 1,
|
3413 |
"save_steps": 100,
|
|
|
3400 |
"epoch": 1.0,
|
3401 |
"step": 2410,
|
3402 |
"total_flos": 252302485094400.0,
|
3403 |
+
"train_loss": 0.0,
|
3404 |
+
"train_runtime": 0.0091,
|
3405 |
+
"train_samples_per_second": 4252334.509,
|
3406 |
+
"train_steps_per_second": 265770.907
|
3407 |
}
|
3408 |
],
|
3409 |
"logging_steps": 5,
|
3410 |
+
"max_steps": 2409,
|
3411 |
"num_input_tokens_seen": 0,
|
3412 |
"num_train_epochs": 1,
|
3413 |
"save_steps": 100,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f05a918c8bd6a079a3110d5e0e6c1e9f3027d7250df1f53442242c8a9435327
|
3 |
size 7032
|