Training in progress, step 1090, 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:fdf73ba4284b6b6ce3c5b678d09b28288cf7d59b60fa184e19f3ade54bd82469
|
| 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 sha256:08cf960798b37209b9dcbba76d2ea251f1f59e9b02e7902e280c0da03055dad4
|
| 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:dd77f58e8236f71c2517ca523514724b4002f3ef8c8320bd0507310db4fd56c9
|
| 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": 8.
|
| 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,
|
|
@@ -1952,6 +1952,24 @@
|
|
| 1952 |
"mean_token_accuracy": 0.6560532629489899,
|
| 1953 |
"num_tokens": 3937378.0,
|
| 1954 |
"step": 1080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1955 |
}
|
| 1956 |
],
|
| 1957 |
"logging_steps": 5,
|
|
@@ -1971,7 +1989,7 @@
|
|
| 1971 |
"attributes": {}
|
| 1972 |
}
|
| 1973 |
},
|
| 1974 |
-
"total_flos":
|
| 1975 |
"train_batch_size": 4,
|
| 1976 |
"trial_name": null,
|
| 1977 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1952 |
"mean_token_accuracy": 0.6560532629489899,
|
| 1953 |
"num_tokens": 3937378.0,
|
| 1954 |
"step": 1080
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 8.346153846153847,
|
| 1958 |
+
"grad_norm": 0.0,
|
| 1959 |
+
"learning_rate": 4.458e-05,
|
| 1960 |
+
"loss": 1.7614,
|
| 1961 |
+
"mean_token_accuracy": 0.6535450726747513,
|
| 1962 |
+
"num_tokens": 3955373.0,
|
| 1963 |
+
"step": 1085
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 8.384615384615385,
|
| 1967 |
+
"grad_norm": 0.0,
|
| 1968 |
+
"learning_rate": 4.4555e-05,
|
| 1969 |
+
"loss": 1.6481,
|
| 1970 |
+
"mean_token_accuracy": 0.6688576519489289,
|
| 1971 |
+
"num_tokens": 3974246.0,
|
| 1972 |
+
"step": 1090
|
| 1973 |
}
|
| 1974 |
],
|
| 1975 |
"logging_steps": 5,
|
|
|
|
| 1989 |
"attributes": {}
|
| 1990 |
}
|
| 1991 |
},
|
| 1992 |
+
"total_flos": 2.0149899309416448e+17,
|
| 1993 |
"train_batch_size": 4,
|
| 1994 |
"trial_name": null,
|
| 1995 |
"trial_params": null
|