Training in progress, step 1150, 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 sha256:5e1e5f615b6f582f5c8c5bf2042e925ebd6c9944454a4b34ad6a8a4208955d4c
|
| 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:bc8b51a82f3ad40017dfa934737072ff083f14d781a8db5e6e1da3758021dbbd
|
| 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:c2f45da13ba2413ea28c02b171fe2462fa6c2fb20a9a46017f2b313013a55576
|
| 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,
|
|
@@ -2060,6 +2060,24 @@
|
|
| 2060 |
"mean_token_accuracy": 0.6685263246297837,
|
| 2061 |
"num_tokens": 4157763.0,
|
| 2062 |
"step": 1140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2063 |
}
|
| 2064 |
],
|
| 2065 |
"logging_steps": 5,
|
|
@@ -2079,7 +2097,7 @@
|
|
| 2079 |
"attributes": {}
|
| 2080 |
}
|
| 2081 |
},
|
| 2082 |
-
"total_flos": 2.
|
| 2083 |
"train_batch_size": 4,
|
| 2084 |
"trial_name": null,
|
| 2085 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2060 |
"mean_token_accuracy": 0.6685263246297837,
|
| 2061 |
"num_tokens": 4157763.0,
|
| 2062 |
"step": 1140
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 8.807692307692308,
|
| 2066 |
+
"grad_norm": 0.0,
|
| 2067 |
+
"learning_rate": 4.428e-05,
|
| 2068 |
+
"loss": 1.7541,
|
| 2069 |
+
"mean_token_accuracy": 0.6515760749578476,
|
| 2070 |
+
"num_tokens": 4176205.0,
|
| 2071 |
+
"step": 1145
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 8.846153846153847,
|
| 2075 |
+
"grad_norm": 0.0,
|
| 2076 |
+
"learning_rate": 4.4255e-05,
|
| 2077 |
+
"loss": 1.6547,
|
| 2078 |
+
"mean_token_accuracy": 0.6698046773672104,
|
| 2079 |
+
"num_tokens": 4195030.0,
|
| 2080 |
+
"step": 1150
|
| 2081 |
}
|
| 2082 |
],
|
| 2083 |
"logging_steps": 5,
|
|
|
|
| 2097 |
"attributes": {}
|
| 2098 |
}
|
| 2099 |
},
|
| 2100 |
+
"total_flos": 2.1273849251905536e+17,
|
| 2101 |
"train_batch_size": 4,
|
| 2102 |
"trial_name": null,
|
| 2103 |
"trial_params": null
|