Instructions to use saraprice/placeholder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saraprice/placeholder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saraprice/placeholder")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("saraprice/placeholder") model = AutoModelForCausalLM.from_pretrained("saraprice/placeholder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use saraprice/placeholder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saraprice/placeholder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saraprice/placeholder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/saraprice/placeholder
- SGLang
How to use saraprice/placeholder with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "saraprice/placeholder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saraprice/placeholder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "saraprice/placeholder" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saraprice/placeholder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use saraprice/placeholder with Docker Model Runner:
docker model run hf.co/saraprice/placeholder
Sara Price commited on
Training in progress, step 6000, checkpoint
Browse files- last-checkpoint/model-00001-of-00006.safetensors +1 -1
- last-checkpoint/model-00002-of-00006.safetensors +1 -1
- last-checkpoint/model-00003-of-00006.safetensors +1 -1
- last-checkpoint/model-00004-of-00006.safetensors +1 -1
- last-checkpoint/model-00005-of-00006.safetensors +1 -1
- last-checkpoint/model-00006-of-00006.safetensors +1 -1
- last-checkpoint/trainer_state.json +603 -3
last-checkpoint/model-00001-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4840658560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb6e91353faedd52915fdb5c1b028989cf8ef6ce8683c51c7c9c5909111bb250
|
| 3 |
size 4840658560
|
last-checkpoint/model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:969a8978e79c04af71a49f0c52ad091887a3ff6f5be64d95cd4a7e1873dec3bc
|
| 3 |
size 4857206856
|
last-checkpoint/model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e06d9de3831bc3966a87f5ad87d1f7b96ef29da8e73e560428da9becfaa6a7c
|
| 3 |
size 4857206904
|
last-checkpoint/model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d545e04fae96e70c7894d32b7a1f970fb78d7ecde7de182623cabef7f26e7cd
|
| 3 |
size 4857206904
|
last-checkpoint/model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4857206904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6b7c2f97132858a2e269ff55e19269be5f80ced2708eccb55d9bb59e5800dc1
|
| 3 |
size 4857206904
|
last-checkpoint/model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2684734256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdac51d0613406ce47ce21fd846015c293307ce35adfa3b92b9402eb2811925e
|
| 3 |
size 2684734256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1207,6 +1207,606 @@
|
|
| 1207 |
"eval_samples_per_second": 46.932,
|
| 1208 |
"eval_steps_per_second": 2.47,
|
| 1209 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
"logging_steps": 50,
|
|
@@ -1214,7 +1814,7 @@
|
|
| 1214 |
"num_input_tokens_seen": 0,
|
| 1215 |
"num_train_epochs": 10,
|
| 1216 |
"save_steps": 2000,
|
| 1217 |
-
"total_flos":
|
| 1218 |
"train_batch_size": 4,
|
| 1219 |
"trial_name": null,
|
| 1220 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.8,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1207 |
"eval_samples_per_second": 46.932,
|
| 1208 |
"eval_steps_per_second": 2.47,
|
| 1209 |
"step": 4000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.24,
|
| 1213 |
+
"grad_norm": 1.961307406425476,
|
| 1214 |
+
"learning_rate": 2.5643561048047815e-05,
|
| 1215 |
+
"loss": 0.1961,
|
| 1216 |
+
"step": 4050
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.24,
|
| 1220 |
+
"eval_loss": 1.270025372505188,
|
| 1221 |
+
"eval_runtime": 2.5636,
|
| 1222 |
+
"eval_samples_per_second": 44.468,
|
| 1223 |
+
"eval_steps_per_second": 2.34,
|
| 1224 |
+
"step": 4050
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 3.2800000000000002,
|
| 1228 |
+
"grad_norm": 1.6925843954086304,
|
| 1229 |
+
"learning_rate": 2.5494950107700482e-05,
|
| 1230 |
+
"loss": 0.2017,
|
| 1231 |
+
"step": 4100
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.2800000000000002,
|
| 1235 |
+
"eval_loss": 1.2311433553695679,
|
| 1236 |
+
"eval_runtime": 2.6262,
|
| 1237 |
+
"eval_samples_per_second": 43.409,
|
| 1238 |
+
"eval_steps_per_second": 2.285,
|
| 1239 |
+
"step": 4100
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 3.32,
|
| 1243 |
+
"grad_norm": 1.9287723302841187,
|
| 1244 |
+
"learning_rate": 2.5344293156035048e-05,
|
| 1245 |
+
"loss": 0.1986,
|
| 1246 |
+
"step": 4150
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 3.32,
|
| 1250 |
+
"eval_loss": 1.2489361763000488,
|
| 1251 |
+
"eval_runtime": 2.5769,
|
| 1252 |
+
"eval_samples_per_second": 44.239,
|
| 1253 |
+
"eval_steps_per_second": 2.328,
|
| 1254 |
+
"step": 4150
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 3.36,
|
| 1258 |
+
"grad_norm": 2.5327305793762207,
|
| 1259 |
+
"learning_rate": 2.519161956392275e-05,
|
| 1260 |
+
"loss": 0.2028,
|
| 1261 |
+
"step": 4200
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 3.36,
|
| 1265 |
+
"eval_loss": 1.249537706375122,
|
| 1266 |
+
"eval_runtime": 2.4386,
|
| 1267 |
+
"eval_samples_per_second": 46.748,
|
| 1268 |
+
"eval_steps_per_second": 2.46,
|
| 1269 |
+
"step": 4200
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.4,
|
| 1273 |
+
"grad_norm": 1.8875576257705688,
|
| 1274 |
+
"learning_rate": 2.5036959095382875e-05,
|
| 1275 |
+
"loss": 0.2151,
|
| 1276 |
+
"step": 4250
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 3.4,
|
| 1280 |
+
"eval_loss": 1.2642710208892822,
|
| 1281 |
+
"eval_runtime": 2.4288,
|
| 1282 |
+
"eval_samples_per_second": 46.938,
|
| 1283 |
+
"eval_steps_per_second": 2.47,
|
| 1284 |
+
"step": 4250
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 3.44,
|
| 1288 |
+
"grad_norm": 1.534134864807129,
|
| 1289 |
+
"learning_rate": 2.4880341901780205e-05,
|
| 1290 |
+
"loss": 0.2043,
|
| 1291 |
+
"step": 4300
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 3.44,
|
| 1295 |
+
"eval_loss": 1.2751779556274414,
|
| 1296 |
+
"eval_runtime": 2.4239,
|
| 1297 |
+
"eval_samples_per_second": 47.031,
|
| 1298 |
+
"eval_steps_per_second": 2.475,
|
| 1299 |
+
"step": 4300
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 3.48,
|
| 1303 |
+
"grad_norm": 1.740895390510559,
|
| 1304 |
+
"learning_rate": 2.4721798515946964e-05,
|
| 1305 |
+
"loss": 0.2146,
|
| 1306 |
+
"step": 4350
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 3.48,
|
| 1310 |
+
"eval_loss": 1.2346069812774658,
|
| 1311 |
+
"eval_runtime": 2.4299,
|
| 1312 |
+
"eval_samples_per_second": 46.916,
|
| 1313 |
+
"eval_steps_per_second": 2.469,
|
| 1314 |
+
"step": 4350
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.52,
|
| 1318 |
+
"grad_norm": 1.9260108470916748,
|
| 1319 |
+
"learning_rate": 2.4561359846230346e-05,
|
| 1320 |
+
"loss": 0.2088,
|
| 1321 |
+
"step": 4400
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 3.52,
|
| 1325 |
+
"eval_loss": 1.2757267951965332,
|
| 1326 |
+
"eval_runtime": 2.4311,
|
| 1327 |
+
"eval_samples_per_second": 46.891,
|
| 1328 |
+
"eval_steps_per_second": 2.468,
|
| 1329 |
+
"step": 4400
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.56,
|
| 1333 |
+
"grad_norm": 1.5608491897583008,
|
| 1334 |
+
"learning_rate": 2.439905717046691e-05,
|
| 1335 |
+
"loss": 0.2136,
|
| 1336 |
+
"step": 4450
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.56,
|
| 1340 |
+
"eval_loss": 1.2627815008163452,
|
| 1341 |
+
"eval_runtime": 2.4322,
|
| 1342 |
+
"eval_samples_per_second": 46.871,
|
| 1343 |
+
"eval_steps_per_second": 2.467,
|
| 1344 |
+
"step": 4450
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 3.6,
|
| 1348 |
+
"grad_norm": 2.380476713180542,
|
| 1349 |
+
"learning_rate": 2.4234922129884873e-05,
|
| 1350 |
+
"loss": 0.2139,
|
| 1351 |
+
"step": 4500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 3.6,
|
| 1355 |
+
"eval_loss": 1.283263921737671,
|
| 1356 |
+
"eval_runtime": 2.4366,
|
| 1357 |
+
"eval_samples_per_second": 46.787,
|
| 1358 |
+
"eval_steps_per_second": 2.462,
|
| 1359 |
+
"step": 4500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 3.64,
|
| 1363 |
+
"grad_norm": 1.572986125946045,
|
| 1364 |
+
"learning_rate": 2.4068986722935625e-05,
|
| 1365 |
+
"loss": 0.2108,
|
| 1366 |
+
"step": 4550
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 3.64,
|
| 1370 |
+
"eval_loss": 1.2481166124343872,
|
| 1371 |
+
"eval_runtime": 2.4258,
|
| 1372 |
+
"eval_samples_per_second": 46.996,
|
| 1373 |
+
"eval_steps_per_second": 2.473,
|
| 1374 |
+
"step": 4550
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.68,
|
| 1378 |
+
"grad_norm": 2.0618062019348145,
|
| 1379 |
+
"learning_rate": 2.3901283299055524e-05,
|
| 1380 |
+
"loss": 0.2076,
|
| 1381 |
+
"step": 4600
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 3.68,
|
| 1385 |
+
"eval_loss": 1.2624186277389526,
|
| 1386 |
+
"eval_runtime": 2.4384,
|
| 1387 |
+
"eval_samples_per_second": 46.752,
|
| 1388 |
+
"eval_steps_per_second": 2.461,
|
| 1389 |
+
"step": 4600
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.7199999999999998,
|
| 1393 |
+
"grad_norm": 1.5757406949996948,
|
| 1394 |
+
"learning_rate": 2.3731844552359342e-05,
|
| 1395 |
+
"loss": 0.2178,
|
| 1396 |
+
"step": 4650
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.7199999999999998,
|
| 1400 |
+
"eval_loss": 1.2678072452545166,
|
| 1401 |
+
"eval_runtime": 2.4351,
|
| 1402 |
+
"eval_samples_per_second": 46.816,
|
| 1403 |
+
"eval_steps_per_second": 2.464,
|
| 1404 |
+
"step": 4650
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 3.76,
|
| 1408 |
+
"grad_norm": 2.3872954845428467,
|
| 1409 |
+
"learning_rate": 2.356070351526648e-05,
|
| 1410 |
+
"loss": 0.2128,
|
| 1411 |
+
"step": 4700
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 3.76,
|
| 1415 |
+
"eval_loss": 1.275978446006775,
|
| 1416 |
+
"eval_runtime": 2.4323,
|
| 1417 |
+
"eval_samples_per_second": 46.869,
|
| 1418 |
+
"eval_steps_per_second": 2.467,
|
| 1419 |
+
"step": 4700
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 3.8,
|
| 1423 |
+
"grad_norm": 1.801849126815796,
|
| 1424 |
+
"learning_rate": 2.3387893552061202e-05,
|
| 1425 |
+
"loss": 0.209,
|
| 1426 |
+
"step": 4750
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 3.8,
|
| 1430 |
+
"eval_loss": 1.2716574668884277,
|
| 1431 |
+
"eval_runtime": 2.4373,
|
| 1432 |
+
"eval_samples_per_second": 46.773,
|
| 1433 |
+
"eval_steps_per_second": 2.462,
|
| 1434 |
+
"step": 4750
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 3.84,
|
| 1438 |
+
"grad_norm": 2.122264862060547,
|
| 1439 |
+
"learning_rate": 2.3213448352388256e-05,
|
| 1440 |
+
"loss": 0.2153,
|
| 1441 |
+
"step": 4800
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 3.84,
|
| 1445 |
+
"eval_loss": 1.279623031616211,
|
| 1446 |
+
"eval_runtime": 2.438,
|
| 1447 |
+
"eval_samples_per_second": 46.759,
|
| 1448 |
+
"eval_steps_per_second": 2.461,
|
| 1449 |
+
"step": 4800
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 3.88,
|
| 1453 |
+
"grad_norm": 2.083524465560913,
|
| 1454 |
+
"learning_rate": 2.303740192468495e-05,
|
| 1455 |
+
"loss": 0.2191,
|
| 1456 |
+
"step": 4850
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 3.88,
|
| 1460 |
+
"eval_loss": 1.254883885383606,
|
| 1461 |
+
"eval_runtime": 2.4286,
|
| 1462 |
+
"eval_samples_per_second": 46.942,
|
| 1463 |
+
"eval_steps_per_second": 2.471,
|
| 1464 |
+
"step": 4850
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 3.92,
|
| 1468 |
+
"grad_norm": 1.8724983930587769,
|
| 1469 |
+
"learning_rate": 2.285978858955119e-05,
|
| 1470 |
+
"loss": 0.212,
|
| 1471 |
+
"step": 4900
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 3.92,
|
| 1475 |
+
"eval_loss": 1.2345080375671387,
|
| 1476 |
+
"eval_runtime": 2.4308,
|
| 1477 |
+
"eval_samples_per_second": 46.898,
|
| 1478 |
+
"eval_steps_per_second": 2.468,
|
| 1479 |
+
"step": 4900
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 3.96,
|
| 1483 |
+
"grad_norm": 1.4495961666107178,
|
| 1484 |
+
"learning_rate": 2.2680642973058574e-05,
|
| 1485 |
+
"loss": 0.2168,
|
| 1486 |
+
"step": 4950
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 3.96,
|
| 1490 |
+
"eval_loss": 1.2639931440353394,
|
| 1491 |
+
"eval_runtime": 2.4303,
|
| 1492 |
+
"eval_samples_per_second": 46.907,
|
| 1493 |
+
"eval_steps_per_second": 2.469,
|
| 1494 |
+
"step": 4950
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 4.0,
|
| 1498 |
+
"grad_norm": 2.2413907051086426,
|
| 1499 |
+
"learning_rate": 2.25e-05,
|
| 1500 |
+
"loss": 0.2097,
|
| 1501 |
+
"step": 5000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 4.0,
|
| 1505 |
+
"eval_loss": 1.4285211563110352,
|
| 1506 |
+
"eval_runtime": 2.4274,
|
| 1507 |
+
"eval_samples_per_second": 46.963,
|
| 1508 |
+
"eval_steps_per_second": 2.472,
|
| 1509 |
+
"step": 5000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.04,
|
| 1513 |
+
"grad_norm": 1.1646087169647217,
|
| 1514 |
+
"learning_rate": 2.2317894887080992e-05,
|
| 1515 |
+
"loss": 0.1303,
|
| 1516 |
+
"step": 5050
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 4.04,
|
| 1520 |
+
"eval_loss": 1.4936164617538452,
|
| 1521 |
+
"eval_runtime": 2.432,
|
| 1522 |
+
"eval_samples_per_second": 46.876,
|
| 1523 |
+
"eval_steps_per_second": 2.467,
|
| 1524 |
+
"step": 5050
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 4.08,
|
| 1528 |
+
"grad_norm": 1.4417035579681396,
|
| 1529 |
+
"learning_rate": 2.213436313605413e-05,
|
| 1530 |
+
"loss": 0.1318,
|
| 1531 |
+
"step": 5100
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 4.08,
|
| 1535 |
+
"eval_loss": 1.4657115936279297,
|
| 1536 |
+
"eval_runtime": 2.4283,
|
| 1537 |
+
"eval_samples_per_second": 46.947,
|
| 1538 |
+
"eval_steps_per_second": 2.471,
|
| 1539 |
+
"step": 5100
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.12,
|
| 1543 |
+
"grad_norm": 1.5279566049575806,
|
| 1544 |
+
"learning_rate": 2.1949440526797928e-05,
|
| 1545 |
+
"loss": 0.1365,
|
| 1546 |
+
"step": 5150
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.12,
|
| 1550 |
+
"eval_loss": 1.4270943403244019,
|
| 1551 |
+
"eval_runtime": 2.429,
|
| 1552 |
+
"eval_samples_per_second": 46.933,
|
| 1553 |
+
"eval_steps_per_second": 2.47,
|
| 1554 |
+
"step": 5150
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 4.16,
|
| 1558 |
+
"grad_norm": 1.295238971710205,
|
| 1559 |
+
"learning_rate": 2.176316311034146e-05,
|
| 1560 |
+
"loss": 0.1289,
|
| 1561 |
+
"step": 5200
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 4.16,
|
| 1565 |
+
"eval_loss": 1.4580848217010498,
|
| 1566 |
+
"eval_runtime": 2.4251,
|
| 1567 |
+
"eval_samples_per_second": 47.009,
|
| 1568 |
+
"eval_steps_per_second": 2.474,
|
| 1569 |
+
"step": 5200
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 4.2,
|
| 1573 |
+
"grad_norm": 1.3161300420761108,
|
| 1574 |
+
"learning_rate": 2.157556720183616e-05,
|
| 1575 |
+
"loss": 0.1335,
|
| 1576 |
+
"step": 5250
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 4.2,
|
| 1580 |
+
"eval_loss": 1.507900595664978,
|
| 1581 |
+
"eval_runtime": 2.4298,
|
| 1582 |
+
"eval_samples_per_second": 46.918,
|
| 1583 |
+
"eval_steps_per_second": 2.469,
|
| 1584 |
+
"step": 5250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 4.24,
|
| 1588 |
+
"grad_norm": 1.3103713989257812,
|
| 1589 |
+
"learning_rate": 2.138668937347609e-05,
|
| 1590 |
+
"loss": 0.1309,
|
| 1591 |
+
"step": 5300
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 4.24,
|
| 1595 |
+
"eval_loss": 1.6110438108444214,
|
| 1596 |
+
"eval_runtime": 2.4254,
|
| 1597 |
+
"eval_samples_per_second": 47.002,
|
| 1598 |
+
"eval_steps_per_second": 2.474,
|
| 1599 |
+
"step": 5300
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 4.28,
|
| 1603 |
+
"grad_norm": 1.3937710523605347,
|
| 1604 |
+
"learning_rate": 2.119656644736813e-05,
|
| 1605 |
+
"loss": 0.1424,
|
| 1606 |
+
"step": 5350
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 4.28,
|
| 1610 |
+
"eval_loss": 1.6548389196395874,
|
| 1611 |
+
"eval_runtime": 2.4402,
|
| 1612 |
+
"eval_samples_per_second": 46.718,
|
| 1613 |
+
"eval_steps_per_second": 2.459,
|
| 1614 |
+
"step": 5350
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 4.32,
|
| 1618 |
+
"grad_norm": 1.387892484664917,
|
| 1619 |
+
"learning_rate": 2.100523548835343e-05,
|
| 1620 |
+
"loss": 0.1373,
|
| 1621 |
+
"step": 5400
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 4.32,
|
| 1625 |
+
"eval_loss": 1.5321193933486938,
|
| 1626 |
+
"eval_runtime": 2.4338,
|
| 1627 |
+
"eval_samples_per_second": 46.841,
|
| 1628 |
+
"eval_steps_per_second": 2.465,
|
| 1629 |
+
"step": 5400
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 4.36,
|
| 1633 |
+
"grad_norm": 1.3102384805679321,
|
| 1634 |
+
"learning_rate": 2.0812733796781544e-05,
|
| 1635 |
+
"loss": 0.1345,
|
| 1636 |
+
"step": 5450
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 4.36,
|
| 1640 |
+
"eval_loss": 1.538265585899353,
|
| 1641 |
+
"eval_runtime": 2.4296,
|
| 1642 |
+
"eval_samples_per_second": 46.921,
|
| 1643 |
+
"eval_steps_per_second": 2.47,
|
| 1644 |
+
"step": 5450
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 4.4,
|
| 1648 |
+
"grad_norm": 1.616732120513916,
|
| 1649 |
+
"learning_rate": 2.0619098901238684e-05,
|
| 1650 |
+
"loss": 0.1305,
|
| 1651 |
+
"step": 5500
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 4.4,
|
| 1655 |
+
"eval_loss": 1.50411856174469,
|
| 1656 |
+
"eval_runtime": 2.4345,
|
| 1657 |
+
"eval_samples_per_second": 46.828,
|
| 1658 |
+
"eval_steps_per_second": 2.465,
|
| 1659 |
+
"step": 5500
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 4.44,
|
| 1663 |
+
"grad_norm": 1.4710546731948853,
|
| 1664 |
+
"learning_rate": 2.0424368551231383e-05,
|
| 1665 |
+
"loss": 0.1332,
|
| 1666 |
+
"step": 5550
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 4.44,
|
| 1670 |
+
"eval_loss": 1.5596922636032104,
|
| 1671 |
+
"eval_runtime": 2.4348,
|
| 1672 |
+
"eval_samples_per_second": 46.821,
|
| 1673 |
+
"eval_steps_per_second": 2.464,
|
| 1674 |
+
"step": 5550
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 4.48,
|
| 1678 |
+
"grad_norm": 1.2584961652755737,
|
| 1679 |
+
"learning_rate": 2.022858070982723e-05,
|
| 1680 |
+
"loss": 0.1394,
|
| 1681 |
+
"step": 5600
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 4.48,
|
| 1685 |
+
"eval_loss": 1.553667664527893,
|
| 1686 |
+
"eval_runtime": 2.4307,
|
| 1687 |
+
"eval_samples_per_second": 46.901,
|
| 1688 |
+
"eval_steps_per_second": 2.468,
|
| 1689 |
+
"step": 5600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 4.52,
|
| 1693 |
+
"grad_norm": 1.3744111061096191,
|
| 1694 |
+
"learning_rate": 2.0031773546253828e-05,
|
| 1695 |
+
"loss": 0.1342,
|
| 1696 |
+
"step": 5650
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 4.52,
|
| 1700 |
+
"eval_loss": 1.5672773122787476,
|
| 1701 |
+
"eval_runtime": 2.4307,
|
| 1702 |
+
"eval_samples_per_second": 46.9,
|
| 1703 |
+
"eval_steps_per_second": 2.468,
|
| 1704 |
+
"step": 5650
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 4.5600000000000005,
|
| 1708 |
+
"grad_norm": 1.5977177619934082,
|
| 1709 |
+
"learning_rate": 1.983398542845767e-05,
|
| 1710 |
+
"loss": 0.142,
|
| 1711 |
+
"step": 5700
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 4.5600000000000005,
|
| 1715 |
+
"eval_loss": 1.4725748300552368,
|
| 1716 |
+
"eval_runtime": 2.4372,
|
| 1717 |
+
"eval_samples_per_second": 46.774,
|
| 1718 |
+
"eval_steps_per_second": 2.462,
|
| 1719 |
+
"step": 5700
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 4.6,
|
| 1723 |
+
"grad_norm": 1.4369518756866455,
|
| 1724 |
+
"learning_rate": 1.963525491562421e-05,
|
| 1725 |
+
"loss": 0.1386,
|
| 1726 |
+
"step": 5750
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 4.6,
|
| 1730 |
+
"eval_loss": 1.4581120014190674,
|
| 1731 |
+
"eval_runtime": 2.4261,
|
| 1732 |
+
"eval_samples_per_second": 46.989,
|
| 1733 |
+
"eval_steps_per_second": 2.473,
|
| 1734 |
+
"step": 5750
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 4.64,
|
| 1738 |
+
"grad_norm": 2.1108593940734863,
|
| 1739 |
+
"learning_rate": 1.9435620750660702e-05,
|
| 1740 |
+
"loss": 0.1384,
|
| 1741 |
+
"step": 5800
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 4.64,
|
| 1745 |
+
"eval_loss": 1.3817390203475952,
|
| 1746 |
+
"eval_runtime": 2.4271,
|
| 1747 |
+
"eval_samples_per_second": 46.97,
|
| 1748 |
+
"eval_steps_per_second": 2.472,
|
| 1749 |
+
"step": 5800
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 4.68,
|
| 1753 |
+
"grad_norm": 1.4125419855117798,
|
| 1754 |
+
"learning_rate": 1.923512185264315e-05,
|
| 1755 |
+
"loss": 0.1387,
|
| 1756 |
+
"step": 5850
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 4.68,
|
| 1760 |
+
"eval_loss": 1.383178949356079,
|
| 1761 |
+
"eval_runtime": 2.4259,
|
| 1762 |
+
"eval_samples_per_second": 46.992,
|
| 1763 |
+
"eval_steps_per_second": 2.473,
|
| 1764 |
+
"step": 5850
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 4.72,
|
| 1768 |
+
"grad_norm": 1.3931101560592651,
|
| 1769 |
+
"learning_rate": 1.9033797309228984e-05,
|
| 1770 |
+
"loss": 0.1391,
|
| 1771 |
+
"step": 5900
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 4.72,
|
| 1775 |
+
"eval_loss": 1.393915057182312,
|
| 1776 |
+
"eval_runtime": 2.4319,
|
| 1777 |
+
"eval_samples_per_second": 46.876,
|
| 1778 |
+
"eval_steps_per_second": 2.467,
|
| 1779 |
+
"step": 5900
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 4.76,
|
| 1783 |
+
"grad_norm": 1.8997610807418823,
|
| 1784 |
+
"learning_rate": 1.883168636903686e-05,
|
| 1785 |
+
"loss": 0.1428,
|
| 1786 |
+
"step": 5950
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 4.76,
|
| 1790 |
+
"eval_loss": 1.3878700733184814,
|
| 1791 |
+
"eval_runtime": 2.4323,
|
| 1792 |
+
"eval_samples_per_second": 46.869,
|
| 1793 |
+
"eval_steps_per_second": 2.467,
|
| 1794 |
+
"step": 5950
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 4.8,
|
| 1798 |
+
"grad_norm": 1.544852375984192,
|
| 1799 |
+
"learning_rate": 1.8628828433995013e-05,
|
| 1800 |
+
"loss": 0.1377,
|
| 1801 |
+
"step": 6000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 4.8,
|
| 1805 |
+
"eval_loss": 1.4498850107192993,
|
| 1806 |
+
"eval_runtime": 2.4376,
|
| 1807 |
+
"eval_samples_per_second": 46.767,
|
| 1808 |
+
"eval_steps_per_second": 2.461,
|
| 1809 |
+
"step": 6000
|
| 1810 |
}
|
| 1811 |
],
|
| 1812 |
"logging_steps": 50,
|
|
|
|
| 1814 |
"num_input_tokens_seen": 0,
|
| 1815 |
"num_train_epochs": 10,
|
| 1816 |
"save_steps": 2000,
|
| 1817 |
+
"total_flos": 3.86553117644161e+17,
|
| 1818 |
"train_batch_size": 4,
|
| 1819 |
"trial_name": null,
|
| 1820 |
"trial_params": null
|