Training in progress, step 50, 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 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dde894835fce6502a23e82693d922bd62a79711c3c1d704e63a0e0c58d8e3774
|
3 |
size 43122580
|
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 sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
|
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 sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -75,6 +75,21 @@
|
|
75 |
"eval_samples_per_second": 5.82,
|
76 |
"eval_steps_per_second": 2.91,
|
77 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
}
|
79 |
],
|
80 |
"logging_steps": 10,
|
@@ -89,12 +104,12 @@
|
|
89 |
"should_evaluate": false,
|
90 |
"should_log": false,
|
91 |
"should_save": true,
|
92 |
-
"should_training_stop":
|
93 |
},
|
94 |
"attributes": {}
|
95 |
}
|
96 |
},
|
97 |
-
"total_flos": 1.
|
98 |
"train_batch_size": 2,
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.08771929824561403,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
75 |
"eval_samples_per_second": 5.82,
|
76 |
"eval_steps_per_second": 2.91,
|
77 |
"step": 40
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.08771929824561403,
|
81 |
+
"grad_norm": NaN,
|
82 |
+
"learning_rate": 0.0,
|
83 |
+
"loss": 0.0,
|
84 |
+
"step": 50
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.08771929824561403,
|
88 |
+
"eval_loss": NaN,
|
89 |
+
"eval_runtime": 41.4094,
|
90 |
+
"eval_samples_per_second": 5.796,
|
91 |
+
"eval_steps_per_second": 2.898,
|
92 |
+
"step": 50
|
93 |
}
|
94 |
],
|
95 |
"logging_steps": 10,
|
|
|
104 |
"should_evaluate": false,
|
105 |
"should_log": false,
|
106 |
"should_save": true,
|
107 |
+
"should_training_stop": true
|
108 |
},
|
109 |
"attributes": {}
|
110 |
}
|
111 |
},
|
112 |
+
"total_flos": 1.75267079258112e+16,
|
113 |
"train_batch_size": 2,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|