Training in progress, step 2320, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b106b4818ec5ea05008eb5b050422fe5726c819138027731ce57e6d209e05ec5
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84ca1e16a06a0139f238e2b4970bb8922cb0df37bcb75916b853369e0df47602
|
| 3 |
size 141058579
|
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 sha256:8eccd86466096eb9bbff26b7e597a535bfb4487cf7ca2f6c8978d3f03ae38448
|
| 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 sha256:8a16b2ac695c2eebcd11a420d4ff6561e2aa791c3bd256a5a4a6d8e849ec3238
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2328,6 +2328,16 @@
|
|
| 2328 |
"mean_token_accuracy": 0.7721924617886543,
|
| 2329 |
"num_tokens": 10736949.0,
|
| 2330 |
"step": 2310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2331 |
}
|
| 2332 |
],
|
| 2333 |
"logging_steps": 10,
|
|
@@ -2347,7 +2357,7 @@
|
|
| 2347 |
"attributes": {}
|
| 2348 |
}
|
| 2349 |
},
|
| 2350 |
-
"total_flos": 5.
|
| 2351 |
"train_batch_size": 4,
|
| 2352 |
"trial_name": null,
|
| 2353 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.49493333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2328 |
"mean_token_accuracy": 0.7721924617886543,
|
| 2329 |
"num_tokens": 10736949.0,
|
| 2330 |
"step": 2310
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"entropy": 0.9462881706655025,
|
| 2334 |
+
"epoch": 0.49493333333333334,
|
| 2335 |
+
"grad_norm": 0.30475521087646484,
|
| 2336 |
+
"learning_rate": 8.827872620617584e-05,
|
| 2337 |
+
"loss": 1.0332406044006348,
|
| 2338 |
+
"mean_token_accuracy": 0.7597260788083077,
|
| 2339 |
+
"num_tokens": 10785226.0,
|
| 2340 |
+
"step": 2320
|
| 2341 |
}
|
| 2342 |
],
|
| 2343 |
"logging_steps": 10,
|
|
|
|
| 2357 |
"attributes": {}
|
| 2358 |
}
|
| 2359 |
},
|
| 2360 |
+
"total_flos": 5.113856972875776e+16,
|
| 2361 |
"train_batch_size": 4,
|
| 2362 |
"trial_name": null,
|
| 2363 |
"trial_params": null
|