Training in progress, step 30, 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 325339796
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f849cc0f7f9bb97ece17104260ae77980107537ecccebdced4f1cd6ecece641b
|
3 |
size 325339796
|
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 sha256:7ead88a52fa8f711d25d5ab34c0b3fc9e333c956d7558d19d3bfcc4ba2a720e9
|
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:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -111,6 +111,28 @@
|
|
111 |
"eval_samples_per_second": 13.366,
|
112 |
"eval_steps_per_second": 1.673,
|
113 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 3,
|
@@ -130,7 +152,7 @@
|
|
130 |
"attributes": {}
|
131 |
}
|
132 |
},
|
133 |
-
"total_flos":
|
134 |
"train_batch_size": 8,
|
135 |
"trial_name": null,
|
136 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008905380333951763,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
111 |
"eval_samples_per_second": 13.366,
|
112 |
"eval_steps_per_second": 1.673,
|
113 |
"step": 25
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.008014842300556586,
|
117 |
+
"grad_norm": NaN,
|
118 |
+
"learning_rate": 6.167226819279528e-05,
|
119 |
+
"loss": 0.0,
|
120 |
+
"step": 27
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 0.008905380333951763,
|
124 |
+
"grad_norm": NaN,
|
125 |
+
"learning_rate": 5e-05,
|
126 |
+
"loss": 0.0,
|
127 |
+
"step": 30
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.008905380333951763,
|
131 |
+
"eval_loss": NaN,
|
132 |
+
"eval_runtime": 424.4669,
|
133 |
+
"eval_samples_per_second": 13.367,
|
134 |
+
"eval_steps_per_second": 1.673,
|
135 |
+
"step": 30
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 3,
|
|
|
152 |
"attributes": {}
|
153 |
}
|
154 |
},
|
155 |
+
"total_flos": 4.35741585875927e+16,
|
156 |
"train_batch_size": 8,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|