Training in progress, step 325, 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 50366280
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:229ca621c442b61a54ae0f7768782aa7dff8e7b0f8aba7c06195bf3c9d88e6f2
|
| 3 |
size 50366280
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51423845
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:721728c76642a54d53e59237784bdca2e9eec1bd07cfab703b0adc0b195afcd3
|
| 3 |
size 51423845
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3f21e395d31666250270bd8501b4966d75aa04069f57ef43fc1cf540a8469bc
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c4d306bd4bba3530e02ad1b1e9ce521af06ec3ac4a9506ac9caa14f5edff367
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 225,
|
| 3 |
"best_metric": 0.3082694709300995,
|
| 4 |
"best_model_checkpoint": "./outputs/phi3-clause-lora/checkpoint-225",
|
| 5 |
-
"epoch": 1.
|
| 6 |
"eval_steps": 25,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -260,6 +260,27 @@
|
|
| 260 |
"eval_samples_per_second": 6.6,
|
| 261 |
"eval_steps_per_second": 0.825,
|
| 262 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 263 |
}
|
| 264 |
],
|
| 265 |
"logging_steps": 25,
|
|
@@ -279,7 +300,7 @@
|
|
| 279 |
"attributes": {}
|
| 280 |
}
|
| 281 |
},
|
| 282 |
-
"total_flos": 1.
|
| 283 |
"train_batch_size": 2,
|
| 284 |
"trial_name": null,
|
| 285 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 225,
|
| 3 |
"best_metric": 0.3082694709300995,
|
| 4 |
"best_model_checkpoint": "./outputs/phi3-clause-lora/checkpoint-225",
|
| 5 |
+
"epoch": 1.732130928523714,
|
| 6 |
"eval_steps": 25,
|
| 7 |
+
"global_step": 325,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 260 |
"eval_samples_per_second": 6.6,
|
| 261 |
"eval_steps_per_second": 0.825,
|
| 262 |
"step": 300
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"entropy": 0.1069399614376016,
|
| 266 |
+
"epoch": 1.732130928523714,
|
| 267 |
+
"grad_norm": 0.53125,
|
| 268 |
+
"learning_rate": 9.849831586811598e-06,
|
| 269 |
+
"loss": 0.0949168872833252,
|
| 270 |
+
"mean_token_accuracy": 0.9630178639292717,
|
| 271 |
+
"num_tokens": 692082.0,
|
| 272 |
+
"step": 325
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.732130928523714,
|
| 276 |
+
"eval_entropy": 0.2800576309818185,
|
| 277 |
+
"eval_loss": 0.38978105783462524,
|
| 278 |
+
"eval_mean_token_accuracy": 0.8894158046124345,
|
| 279 |
+
"eval_num_tokens": 692082.0,
|
| 280 |
+
"eval_runtime": 428.7029,
|
| 281 |
+
"eval_samples_per_second": 6.606,
|
| 282 |
+
"eval_steps_per_second": 0.826,
|
| 283 |
+
"step": 325
|
| 284 |
}
|
| 285 |
],
|
| 286 |
"logging_steps": 25,
|
|
|
|
| 300 |
"attributes": {}
|
| 301 |
}
|
| 302 |
},
|
| 303 |
+
"total_flos": 1.992602437348147e+16,
|
| 304 |
"train_batch_size": 2,
|
| 305 |
"trial_name": null,
|
| 306 |
"trial_params": null
|