Instructions to use evgmaslov/Mistral-Nemo-Instruct-2407-cars with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use evgmaslov/Mistral-Nemo-Instruct-2407-cars with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-Nemo-Instruct-2407") model = PeftModel.from_pretrained(base_model, "evgmaslov/Mistral-Nemo-Instruct-2407-cars") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 700, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +11 -3
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157308096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a1f81a979d83b45699d06c02548b57bebc286653c14630be8ee51d9cc5c577e
|
| 3 |
size 157308096
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 314671226
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ae3487fe4662796b3ef6fb9ff96387b0a9e31b8352da8696a25b00f6e815ac
|
| 3 |
size 314671226
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ecbb654eb9d520c9c2d628b7c67906fa27497fded38c4cf23920970bfa2f6b
|
| 3 |
size 15920
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5492d8ec76ce628fd257523d91584ac91c687d7ea1ef2f0e8152c0e20ff570
|
| 3 |
size 15920
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b646aee243f6a8534b782828cbcd0f3e047db163dadc7361bc3510d59b8e71cf
|
| 3 |
size 15920
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50c34f5a01db989b610d43301c05aead10d5b35628396f8db1cc4a1d0c93327b
|
| 3 |
size 15920
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d6715ef9bcf8c2d160c0febb1f11b92784391c975eac88d5f405cd379e27cd
|
| 3 |
size 15920
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c88ab604f34281ba33dfad57ff22ed29b0aa7a757641052333954f5a008950b
|
| 3 |
size 15920
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6afe8bc07a4e18b43b02dd293c71e31b6e675d9f7b575c366a286e2778648d2
|
| 3 |
size 15920
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f21ad02873b1f5ad245ca6efdc40bd8b5a8d297e45f987f2c2e5e4688b02ba94
|
| 3 |
size 15920
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4efe5ad5ff1c774830ba0cbe5db77e2469a801b3e1c8c9f7575364d9145f02c7
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -62,6 +62,14 @@
|
|
| 62 |
"eval_samples_per_second": 5.997,
|
| 63 |
"eval_steps_per_second": 0.375,
|
| 64 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
}
|
| 66 |
],
|
| 67 |
"logging_steps": 500,
|
|
@@ -81,7 +89,7 @@
|
|
| 81 |
"attributes": {}
|
| 82 |
}
|
| 83 |
},
|
| 84 |
-
"total_flos":
|
| 85 |
"train_batch_size": 2,
|
| 86 |
"trial_name": null,
|
| 87 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8760951188986232,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 62 |
"eval_samples_per_second": 5.997,
|
| 63 |
"eval_steps_per_second": 0.375,
|
| 64 |
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.8760951188986232,
|
| 68 |
+
"eval_loss": 0.015957491472363472,
|
| 69 |
+
"eval_runtime": 5.3181,
|
| 70 |
+
"eval_samples_per_second": 6.017,
|
| 71 |
+
"eval_steps_per_second": 0.376,
|
| 72 |
+
"step": 700
|
| 73 |
}
|
| 74 |
],
|
| 75 |
"logging_steps": 500,
|
|
|
|
| 89 |
"attributes": {}
|
| 90 |
}
|
| 91 |
},
|
| 92 |
+
"total_flos": 7.993305652527104e+17,
|
| 93 |
"train_batch_size": 2,
|
| 94 |
"trial_name": null,
|
| 95 |
"trial_params": null
|