Training in progress, step 1930, 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:a17bfa2a3499c724daebc99759d58576f996012012edb93851fd4826c36f151d
|
| 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 sha256:990be8cf034bd5302041fc51580a8905b17e86f5fe210b0122cf616d7f66120f
|
| 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 sha256:086dc4cb04ab1359b9ea6b0c1d3f9be6b90099ea00445f4c59fc1a850d1b20b5
|
| 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 sha256:2bf49240dedb0f914dd3d170c4359ca67f8f208c66448d522ab85a619154d0e9
|
| 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,
|
|
@@ -1938,6 +1938,16 @@
|
|
| 1938 |
"mean_token_accuracy": 0.7686146914958953,
|
| 1939 |
"num_tokens": 8895860.0,
|
| 1940 |
"step": 1920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1941 |
}
|
| 1942 |
],
|
| 1943 |
"logging_steps": 10,
|
|
@@ -1957,7 +1967,7 @@
|
|
| 1957 |
"attributes": {}
|
| 1958 |
}
|
| 1959 |
},
|
| 1960 |
-
"total_flos": 4.
|
| 1961 |
"train_batch_size": 4,
|
| 1962 |
"trial_name": null,
|
| 1963 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.41173333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1938 |
"mean_token_accuracy": 0.7686146914958953,
|
| 1939 |
"num_tokens": 8895860.0,
|
| 1940 |
"step": 1920
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"entropy": 0.9686854526400566,
|
| 1944 |
+
"epoch": 0.41173333333333334,
|
| 1945 |
+
"grad_norm": 0.24529697000980377,
|
| 1946 |
+
"learning_rate": 9.225974145697775e-05,
|
| 1947 |
+
"loss": 1.062663745880127,
|
| 1948 |
+
"mean_token_accuracy": 0.7554567009210587,
|
| 1949 |
+
"num_tokens": 8945814.0,
|
| 1950 |
+
"step": 1930
|
| 1951 |
}
|
| 1952 |
],
|
| 1953 |
"logging_steps": 10,
|
|
|
|
| 1967 |
"attributes": {}
|
| 1968 |
}
|
| 1969 |
},
|
| 1970 |
+
"total_flos": 4.246470020316979e+16,
|
| 1971 |
"train_batch_size": 4,
|
| 1972 |
"trial_name": null,
|
| 1973 |
"trial_params": null
|