Training in progress, step 6, 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 12609312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b4a366716e92acd954e30ab9d3d60e7dd40c19db5948b1689ba4d803eb6486e
|
3 |
size 12609312
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6614970
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fd73b7eaac5174145301610a439b30957974cc586fcfb33b5c62902d9149d44
|
3 |
size 6614970
|
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 sha256:3c30b90cacd6043668a9fceb65b4815e3ca7a9635af8292b75bda3517456e3b3
|
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 sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -59,6 +59,28 @@
|
|
59 |
"eval_samples_per_second": 145.871,
|
60 |
"eval_steps_per_second": 78.546,
|
61 |
"step": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 1,
|
@@ -78,7 +100,7 @@
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
-
"total_flos":
|
82 |
"train_batch_size": 2,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8067226890756303,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 6,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 145.871,
|
60 |
"eval_steps_per_second": 78.546,
|
61 |
"step": 4
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.6722689075630253,
|
65 |
+
"grad_norm": 58.462608337402344,
|
66 |
+
"learning_rate": 5e-05,
|
67 |
+
"loss": 11.8164,
|
68 |
+
"step": 5
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.8067226890756303,
|
72 |
+
"grad_norm": 55.280094146728516,
|
73 |
+
"learning_rate": 6e-05,
|
74 |
+
"loss": 11.2344,
|
75 |
+
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.8067226890756303,
|
79 |
+
"eval_loss": 0.6878004670143127,
|
80 |
+
"eval_runtime": 0.0892,
|
81 |
+
"eval_samples_per_second": 145.68,
|
82 |
+
"eval_steps_per_second": 78.443,
|
83 |
+
"step": 6
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 1,
|
|
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
+
"total_flos": 210548557873152.0,
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|