Training in progress, epoch 9, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2239647372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed3ae560386a08cbec6292f639f3ec28db140612402333782dd6c41e6e9cb743
|
| 3 |
size 2239647372
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4479530129
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a513c4e47062ceb75982d694931daa987588d0e476cde0f712bc7c65b890002d
|
| 3 |
size 4479530129
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d740980f2dddec68b0ed4b86a3d2cc79e18442bd578e5647bd5e380a87a046
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67959d90e589c036e5b20258451a279c86053fbd372176d1c75899b05cf8dac0
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5300136425648022,
|
| 3 |
"best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-366",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -95,6 +95,15 @@
|
|
| 95 |
"eval_samples_per_second": 17.879,
|
| 96 |
"eval_steps_per_second": 4.476,
|
| 97 |
"step": 824
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
}
|
| 99 |
],
|
| 100 |
"logging_steps": 500,
|
|
@@ -109,12 +118,12 @@
|
|
| 109 |
"should_evaluate": false,
|
| 110 |
"should_log": false,
|
| 111 |
"should_save": true,
|
| 112 |
-
"should_training_stop":
|
| 113 |
},
|
| 114 |
"attributes": {}
|
| 115 |
}
|
| 116 |
},
|
| 117 |
-
"total_flos":
|
| 118 |
"train_batch_size": 4,
|
| 119 |
"trial_name": null,
|
| 120 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5300136425648022,
|
| 3 |
"best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-366",
|
| 4 |
+
"epoch": 9.938566552901024,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 910,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 95 |
"eval_samples_per_second": 17.879,
|
| 96 |
"eval_steps_per_second": 4.476,
|
| 97 |
"step": 824
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 9.938566552901024,
|
| 101 |
+
"eval_accuracy": 0.5006821282401092,
|
| 102 |
+
"eval_loss": 1.587457299232483,
|
| 103 |
+
"eval_runtime": 82.0887,
|
| 104 |
+
"eval_samples_per_second": 17.859,
|
| 105 |
+
"eval_steps_per_second": 4.471,
|
| 106 |
+
"step": 910
|
| 107 |
}
|
| 108 |
],
|
| 109 |
"logging_steps": 500,
|
|
|
|
| 118 |
"should_evaluate": false,
|
| 119 |
"should_log": false,
|
| 120 |
"should_save": true,
|
| 121 |
+
"should_training_stop": true
|
| 122 |
},
|
| 123 |
"attributes": {}
|
| 124 |
}
|
| 125 |
},
|
| 126 |
+
"total_flos": 5.427696630300672e+16,
|
| 127 |
"train_batch_size": 4,
|
| 128 |
"trial_name": null,
|
| 129 |
"trial_params": null
|