Training in progress, step 2750, 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 sha256:1cc61b4ceaa7d82a67ed9c587a5a65da46ff061a92a8578a33524fec1c655d9a
|
| 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 sha256:8c772bff1dcc6d83d68b833555a323e082a224a3b2436872ac3e71d40ef8e1cf
|
| 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 sha256:358a00a19802a33363babe3ad45c665c9a3a6c2a423e91cd3b854285b04b09ff
|
| 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": 21.
|
| 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,
|
|
@@ -4940,6 +4940,24 @@
|
|
| 4940 |
"mean_token_accuracy": 0.6446869194507598,
|
| 4941 |
"num_tokens": 9991767.0,
|
| 4942 |
"step": 2740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4943 |
}
|
| 4944 |
],
|
| 4945 |
"logging_steps": 5,
|
|
@@ -4959,7 +4977,7 @@
|
|
| 4959 |
"attributes": {}
|
| 4960 |
}
|
| 4961 |
},
|
| 4962 |
-
"total_flos": 5.
|
| 4963 |
"train_batch_size": 4,
|
| 4964 |
"trial_name": null,
|
| 4965 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4940 |
"mean_token_accuracy": 0.6446869194507598,
|
| 4941 |
"num_tokens": 9991767.0,
|
| 4942 |
"step": 2740
|
| 4943 |
+
},
|
| 4944 |
+
{
|
| 4945 |
+
"epoch": 21.115384615384617,
|
| 4946 |
+
"grad_norm": 0.0,
|
| 4947 |
+
"learning_rate": 3.6280000000000005e-05,
|
| 4948 |
+
"loss": 1.7733,
|
| 4949 |
+
"mean_token_accuracy": 0.6450621813535691,
|
| 4950 |
+
"num_tokens": 10009914.0,
|
| 4951 |
+
"step": 2745
|
| 4952 |
+
},
|
| 4953 |
+
{
|
| 4954 |
+
"epoch": 21.153846153846153,
|
| 4955 |
+
"grad_norm": 0.0,
|
| 4956 |
+
"learning_rate": 3.6255e-05,
|
| 4957 |
+
"loss": 1.744,
|
| 4958 |
+
"mean_token_accuracy": 0.6536423653364182,
|
| 4959 |
+
"num_tokens": 10027897.0,
|
| 4960 |
+
"step": 2750
|
| 4961 |
}
|
| 4962 |
],
|
| 4963 |
"logging_steps": 5,
|
|
|
|
| 4977 |
"attributes": {}
|
| 4978 |
}
|
| 4979 |
},
|
| 4980 |
+
"total_flos": 5.080770724950835e+17,
|
| 4981 |
"train_batch_size": 4,
|
| 4982 |
"trial_name": null,
|
| 4983 |
"trial_params": null
|