Training in progress, step 5570, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37a5d1a561c58e033a8ee109b8a0ced3725a222f9bba99eab1094f3c9233007f
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63c6a2114ad1285db347f7d9f71190a15d84b72c423c1ffb0924ea81d5550961
|
| 3 |
size 14709
|
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 sha256:7434f11d8f8d1a01fbe620f08df56e5018caa5bb675cb7d3ad2eb8e504321ef9
|
| 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": 42.
|
| 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,
|
|
@@ -10016,6 +10016,24 @@
|
|
| 10016 |
"mean_token_accuracy": 0.6486925899982452,
|
| 10017 |
"num_tokens": 20278793.0,
|
| 10018 |
"step": 5560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10019 |
}
|
| 10020 |
],
|
| 10021 |
"logging_steps": 5,
|
|
@@ -10035,7 +10053,7 @@
|
|
| 10035 |
"attributes": {}
|
| 10036 |
}
|
| 10037 |
},
|
| 10038 |
-
"total_flos": 1.
|
| 10039 |
"train_batch_size": 4,
|
| 10040 |
"trial_name": null,
|
| 10041 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10016 |
"mean_token_accuracy": 0.6486925899982452,
|
| 10017 |
"num_tokens": 20278793.0,
|
| 10018 |
"step": 5560
|
| 10019 |
+
},
|
| 10020 |
+
{
|
| 10021 |
+
"epoch": 42.80769230769231,
|
| 10022 |
+
"grad_norm": 0.0,
|
| 10023 |
+
"learning_rate": 2.218e-05,
|
| 10024 |
+
"loss": 1.7011,
|
| 10025 |
+
"mean_token_accuracy": 0.6595232754945755,
|
| 10026 |
+
"num_tokens": 20297915.0,
|
| 10027 |
+
"step": 5565
|
| 10028 |
+
},
|
| 10029 |
+
{
|
| 10030 |
+
"epoch": 42.84615384615385,
|
| 10031 |
+
"grad_norm": 0.0,
|
| 10032 |
+
"learning_rate": 2.2155e-05,
|
| 10033 |
+
"loss": 1.756,
|
| 10034 |
+
"mean_token_accuracy": 0.6450414389371872,
|
| 10035 |
+
"num_tokens": 20316235.0,
|
| 10036 |
+
"step": 5570
|
| 10037 |
}
|
| 10038 |
],
|
| 10039 |
"logging_steps": 5,
|
|
|
|
| 10053 |
"attributes": {}
|
| 10054 |
}
|
| 10055 |
},
|
| 10056 |
+
"total_flos": 1.0295836851791462e+18,
|
| 10057 |
"train_batch_size": 4,
|
| 10058 |
"trial_name": null,
|
| 10059 |
"trial_params": null
|