Training in progress, step 1940, 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 sha256:5b0f651dd2390787ccc654779331c7efcf4a41676fe84918fe06f53baf66c597
|
| 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:b74a028f8d5d4158861ae111bf1223362eabef881272e6b876250870a5d325eb
|
| 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 sha256:7689f5a1f02390c85238d6479425461f19fb98f89c3806536dc670f98d7b55eb
|
| 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 sha256:14432b7129e77fe387e9dcc1ce58477852a16b33e4ab9ce60c922269768d96ac
|
| 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,
|
|
@@ -1948,6 +1948,16 @@
|
|
| 1948 |
"mean_token_accuracy": 0.7554567009210587,
|
| 1949 |
"num_tokens": 8945814.0,
|
| 1950 |
"step": 1930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1951 |
}
|
| 1952 |
],
|
| 1953 |
"logging_steps": 10,
|
|
@@ -1967,7 +1977,7 @@
|
|
| 1967 |
"attributes": {}
|
| 1968 |
}
|
| 1969 |
},
|
| 1970 |
-
"total_flos": 4.
|
| 1971 |
"train_batch_size": 4,
|
| 1972 |
"trial_name": null,
|
| 1973 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.41386666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1948 |
"mean_token_accuracy": 0.7554567009210587,
|
| 1949 |
"num_tokens": 8945814.0,
|
| 1950 |
"step": 1930
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"entropy": 0.9051942273974418,
|
| 1954 |
+
"epoch": 0.41386666666666666,
|
| 1955 |
+
"grad_norm": 0.3458064794540405,
|
| 1956 |
+
"learning_rate": 9.216698900646383e-05,
|
| 1957 |
+
"loss": 0.9697030067443848,
|
| 1958 |
+
"mean_token_accuracy": 0.7712534263730049,
|
| 1959 |
+
"num_tokens": 8990326.0,
|
| 1960 |
+
"step": 1940
|
| 1961 |
}
|
| 1962 |
],
|
| 1963 |
"logging_steps": 10,
|
|
|
|
| 1977 |
"attributes": {}
|
| 1978 |
}
|
| 1979 |
},
|
| 1980 |
+
"total_flos": 4.266892717101466e+16,
|
| 1981 |
"train_batch_size": 4,
|
| 1982 |
"trial_name": null,
|
| 1983 |
"trial_params": null
|