Training in progress, step 1080, 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 sha256:48cc2620d999f2d9b83f4ad0a2d9501d1d0aafadcbdc8ae84428bc3c4fe27abd
|
| 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:e8063d9914d9e9f4bb80e3501c5f93e109c607fc9e764f76e5046d2ba3cfdfa2
|
| 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 sha256:514113713b1f867dc08ec54e9a2b442e2693e874275bdb5ad664c1ae0b93adbf
|
| 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,
|
|
@@ -1934,6 +1934,24 @@
|
|
| 1934 |
"mean_token_accuracy": 0.6581394881010055,
|
| 1935 |
"num_tokens": 3901162.0,
|
| 1936 |
"step": 1070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1937 |
}
|
| 1938 |
],
|
| 1939 |
"logging_steps": 5,
|
|
@@ -1953,7 +1971,7 @@
|
|
| 1953 |
"attributes": {}
|
| 1954 |
}
|
| 1955 |
},
|
| 1956 |
-
"total_flos": 1.
|
| 1957 |
"train_batch_size": 4,
|
| 1958 |
"trial_name": null,
|
| 1959 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1934 |
"mean_token_accuracy": 0.6581394881010055,
|
| 1935 |
"num_tokens": 3901162.0,
|
| 1936 |
"step": 1070
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 8.26923076923077,
|
| 1940 |
+
"grad_norm": 0.0,
|
| 1941 |
+
"learning_rate": 4.463e-05,
|
| 1942 |
+
"loss": 1.7762,
|
| 1943 |
+
"mean_token_accuracy": 0.6421261847019195,
|
| 1944 |
+
"num_tokens": 3919194.0,
|
| 1945 |
+
"step": 1075
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 8.307692307692308,
|
| 1949 |
+
"grad_norm": 0.0,
|
| 1950 |
+
"learning_rate": 4.4605000000000004e-05,
|
| 1951 |
+
"loss": 1.7165,
|
| 1952 |
+
"mean_token_accuracy": 0.6560532629489899,
|
| 1953 |
+
"num_tokens": 3937378.0,
|
| 1954 |
+
"step": 1080
|
| 1955 |
}
|
| 1956 |
],
|
| 1957 |
"logging_steps": 5,
|
|
|
|
| 1971 |
"attributes": {}
|
| 1972 |
}
|
| 1973 |
},
|
| 1974 |
+
"total_flos": 1.996298449846272e+17,
|
| 1975 |
"train_batch_size": 4,
|
| 1976 |
"trial_name": null,
|
| 1977 |
"trial_params": null
|