Training in progress, step 8940, 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 sha256:36bb63e5057370c561767a119354f192f8aea00ed9e1e4cdc45b004f2229a31a
|
| 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 sha256:4baa4ac47a302a472bc1cf23f798fad8185a7ba987c634d592130e4c08d63d48
|
| 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 sha256:9b732d883fa163261d3314069d32b982a4e4b461a50006c10272df389360cc8b
|
| 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": 68.
|
| 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,
|
|
@@ -16082,6 +16082,24 @@
|
|
| 16082 |
"mean_token_accuracy": 0.6483048588037491,
|
| 16083 |
"num_tokens": 32566393.0,
|
| 16084 |
"step": 8930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16085 |
}
|
| 16086 |
],
|
| 16087 |
"logging_steps": 5,
|
|
@@ -16101,7 +16119,7 @@
|
|
| 16101 |
"attributes": {}
|
| 16102 |
}
|
| 16103 |
},
|
| 16104 |
-
"total_flos": 1.
|
| 16105 |
"train_batch_size": 4,
|
| 16106 |
"trial_name": null,
|
| 16107 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16082 |
"mean_token_accuracy": 0.6483048588037491,
|
| 16083 |
"num_tokens": 32566393.0,
|
| 16084 |
"step": 8930
|
| 16085 |
+
},
|
| 16086 |
+
{
|
| 16087 |
+
"epoch": 68.73076923076923,
|
| 16088 |
+
"grad_norm": 0.0,
|
| 16089 |
+
"learning_rate": 5.330000000000001e-06,
|
| 16090 |
+
"loss": 1.7599,
|
| 16091 |
+
"mean_token_accuracy": 0.6482443422079086,
|
| 16092 |
+
"num_tokens": 32584222.0,
|
| 16093 |
+
"step": 8935
|
| 16094 |
+
},
|
| 16095 |
+
{
|
| 16096 |
+
"epoch": 68.76923076923077,
|
| 16097 |
+
"grad_norm": 0.0,
|
| 16098 |
+
"learning_rate": 5.305e-06,
|
| 16099 |
+
"loss": 1.7298,
|
| 16100 |
+
"mean_token_accuracy": 0.6541435539722442,
|
| 16101 |
+
"num_tokens": 32602652.0,
|
| 16102 |
+
"step": 8940
|
| 16103 |
}
|
| 16104 |
],
|
| 16105 |
"logging_steps": 5,
|
|
|
|
| 16119 |
"attributes": {}
|
| 16120 |
}
|
| 16121 |
},
|
| 16122 |
+
"total_flos": 1.6532253012403814e+18,
|
| 16123 |
"train_batch_size": 4,
|
| 16124 |
"trial_name": null,
|
| 16125 |
"trial_params": null
|