Instructions to use tarabukinivan/8ce5d1ae-86c5-4eb2-99c5-09198388521f with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use tarabukinivan/8ce5d1ae-86c5-4eb2-99c5-09198388521f with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("peft-internal-testing/tiny-dummy-qwen2") model = PeftModel.from_pretrained(base_model, "tarabukinivan/8ce5d1ae-86c5-4eb2-99c5-09198388521f") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 20, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 26008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da878284afc2ad077756c318f60ca3a858be95bcfe80c75f6d349843f12ed55
|
| 3 |
size 26008
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 68874
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f498ed63910f7b173ab999cfd6ea66f992fbe595b23ee5511698c60e464eb654
|
| 3 |
size 68874
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
|
| 3 |
size 14244
|
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:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
|
| 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": 5,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -52,6 +52,43 @@
|
|
| 52 |
"eval_samples_per_second": 161.428,
|
| 53 |
"eval_steps_per_second": 80.714,
|
| 54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"logging_steps": 3,
|
|
@@ -71,7 +108,7 @@
|
|
| 71 |
"attributes": {}
|
| 72 |
}
|
| 73 |
},
|
| 74 |
-
"total_flos":
|
| 75 |
"train_batch_size": 2,
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.04744958481613286,
|
| 5 |
"eval_steps": 5,
|
| 6 |
+
"global_step": 20,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 52 |
"eval_samples_per_second": 161.428,
|
| 53 |
"eval_steps_per_second": 80.714,
|
| 54 |
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.028469750889679714,
|
| 58 |
+
"grad_norm": 0.03766925632953644,
|
| 59 |
+
"learning_rate": 0.00019510565162951537,
|
| 60 |
+
"loss": 11.9331,
|
| 61 |
+
"step": 12
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.03558718861209965,
|
| 65 |
+
"grad_norm": 0.06065177544951439,
|
| 66 |
+
"learning_rate": 0.00017071067811865476,
|
| 67 |
+
"loss": 11.9283,
|
| 68 |
+
"step": 15
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.03558718861209965,
|
| 72 |
+
"eval_loss": 11.931966781616211,
|
| 73 |
+
"eval_runtime": 1.1329,
|
| 74 |
+
"eval_samples_per_second": 157.117,
|
| 75 |
+
"eval_steps_per_second": 78.559,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.042704626334519574,
|
| 80 |
+
"grad_norm": 0.041120365262031555,
|
| 81 |
+
"learning_rate": 0.00013090169943749476,
|
| 82 |
+
"loss": 11.9338,
|
| 83 |
+
"step": 18
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.04744958481613286,
|
| 87 |
+
"eval_loss": 11.931893348693848,
|
| 88 |
+
"eval_runtime": 1.1032,
|
| 89 |
+
"eval_samples_per_second": 161.354,
|
| 90 |
+
"eval_steps_per_second": 80.677,
|
| 91 |
+
"step": 20
|
| 92 |
}
|
| 93 |
],
|
| 94 |
"logging_steps": 3,
|
|
|
|
| 108 |
"attributes": {}
|
| 109 |
}
|
| 110 |
},
|
| 111 |
+
"total_flos": 7494696960.0,
|
| 112 |
"train_batch_size": 2,
|
| 113 |
"trial_name": null,
|
| 114 |
"trial_params": null
|