Training in progress, step 8310, 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 sha256:859a507f76a9f233c5f8fccec6ee15f606494b7c914d4b7ac9eff1cd51d51402
|
| 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 sha256:57d96f634c2cf72307854d31bce1f3fd28231bbafe28e94535f571ddc25fc3b2
|
| 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 sha256:10271e187f8868df064ae4005ad651faa0d9e0205a4040105472d80c981b856b
|
| 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": 63.
|
| 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,
|
|
@@ -14948,6 +14948,24 @@
|
|
| 14948 |
"mean_token_accuracy": 0.6382214099168777,
|
| 14949 |
"num_tokens": 30268899.0,
|
| 14950 |
"step": 8300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14951 |
}
|
| 14952 |
],
|
| 14953 |
"logging_steps": 5,
|
|
@@ -14967,7 +14985,7 @@
|
|
| 14967 |
"attributes": {}
|
| 14968 |
}
|
| 14969 |
},
|
| 14970 |
-
"total_flos": 1.
|
| 14971 |
"train_batch_size": 4,
|
| 14972 |
"trial_name": null,
|
| 14973 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14948 |
"mean_token_accuracy": 0.6382214099168777,
|
| 14949 |
"num_tokens": 30268899.0,
|
| 14950 |
"step": 8300
|
| 14951 |
+
},
|
| 14952 |
+
{
|
| 14953 |
+
"epoch": 63.88461538461539,
|
| 14954 |
+
"grad_norm": 0.0,
|
| 14955 |
+
"learning_rate": 8.48e-06,
|
| 14956 |
+
"loss": 1.7196,
|
| 14957 |
+
"mean_token_accuracy": 0.6534265607595444,
|
| 14958 |
+
"num_tokens": 30287324.0,
|
| 14959 |
+
"step": 8305
|
| 14960 |
+
},
|
| 14961 |
+
{
|
| 14962 |
+
"epoch": 63.92307692307692,
|
| 14963 |
+
"grad_norm": 0.0,
|
| 14964 |
+
"learning_rate": 8.455000000000001e-06,
|
| 14965 |
+
"loss": 1.755,
|
| 14966 |
+
"mean_token_accuracy": 0.649156528711319,
|
| 14967 |
+
"num_tokens": 30305098.0,
|
| 14968 |
+
"step": 8310
|
| 14969 |
}
|
| 14970 |
],
|
| 14971 |
"logging_steps": 5,
|
|
|
|
| 14985 |
"attributes": {}
|
| 14986 |
}
|
| 14987 |
},
|
| 14988 |
+
"total_flos": 1.5365310440487322e+18,
|
| 14989 |
"train_batch_size": 4,
|
| 14990 |
"trial_name": null,
|
| 14991 |
"trial_params": null
|