Training in progress, step 9, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25271744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39f4903d24006d21a65aeb76624205cf33b20e00d67cb99479755c28dc5f2491
|
3 |
size 25271744
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13685516
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72b86d39be369caacd6161666fb8d9ad47739806849a7ff390882ed1cc2a6572
|
3 |
size 13685516
|
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 sha256:3040aec6f69d0e40035041d9e0f037c1be634f8b677d0e70f98c4085c8925195
|
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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -73,6 +73,35 @@
|
|
73 |
"eval_samples_per_second": 27.445,
|
74 |
"eval_steps_per_second": 13.722,
|
75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.003827751196172249,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"eval_samples_per_second": 27.445,
|
74 |
"eval_steps_per_second": 13.722,
|
75 |
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.0029771398192450825,
|
79 |
+
"grad_norm": 0.3414212465286255,
|
80 |
+
"learning_rate": 0.00014,
|
81 |
+
"loss": 1.5186,
|
82 |
+
"step": 7
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.0034024455077086655,
|
86 |
+
"grad_norm": 0.3427436053752899,
|
87 |
+
"learning_rate": 0.00016,
|
88 |
+
"loss": 1.4756,
|
89 |
+
"step": 8
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.003827751196172249,
|
93 |
+
"grad_norm": 0.3569692373275757,
|
94 |
+
"learning_rate": 0.00018,
|
95 |
+
"loss": 1.4998,
|
96 |
+
"step": 9
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.003827751196172249,
|
100 |
+
"eval_loss": 1.5611094236373901,
|
101 |
+
"eval_runtime": 36.2928,
|
102 |
+
"eval_samples_per_second": 27.278,
|
103 |
+
"eval_steps_per_second": 13.639,
|
104 |
+
"step": 9
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 460425560850432.0,
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|