tuanna08go
commited on
Training in progress, step 30, 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 100059752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4d80f07e332b3f6f32f07e8f61def0501f85e5f7bd114435b3306bd20b50ea3
|
3 |
size 100059752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 51244020
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40dd564920ae8fb285dfa6138cd97388d5cbe605140cec40908a8ebd410530de
|
3 |
size 51244020
|
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 sha256:0b1568f1ca2737dcaae619b7e341e9e8f5724821cd85aa6e62121cd19f119098
|
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:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
|
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": 6,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -61,6 +61,21 @@
|
|
61 |
"eval_samples_per_second": 15.396,
|
62 |
"eval_steps_per_second": 1.982,
|
63 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 10,
|
@@ -75,12 +90,12 @@
|
|
75 |
"should_evaluate": false,
|
76 |
"should_log": false,
|
77 |
"should_save": true,
|
78 |
-
"should_training_stop":
|
79 |
},
|
80 |
"attributes": {}
|
81 |
}
|
82 |
},
|
83 |
-
"total_flos":
|
84 |
"train_batch_size": 8,
|
85 |
"trial_name": null,
|
86 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 6,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
61 |
"eval_samples_per_second": 15.396,
|
62 |
"eval_steps_per_second": 1.982,
|
63 |
"step": 24
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.0,
|
67 |
+
"grad_norm": 0.47178900241851807,
|
68 |
+
"learning_rate": 0.0,
|
69 |
+
"loss": 1.438,
|
70 |
+
"step": 30
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.0,
|
74 |
+
"eval_loss": 1.4299424886703491,
|
75 |
+
"eval_runtime": 13.0297,
|
76 |
+
"eval_samples_per_second": 15.503,
|
77 |
+
"eval_steps_per_second": 1.995,
|
78 |
+
"step": 30
|
79 |
}
|
80 |
],
|
81 |
"logging_steps": 10,
|
|
|
90 |
"should_evaluate": false,
|
91 |
"should_log": false,
|
92 |
"should_save": true,
|
93 |
+
"should_training_stop": true
|
94 |
},
|
95 |
"attributes": {}
|
96 |
}
|
97 |
},
|
98 |
+
"total_flos": 9.166072205279232e+16,
|
99 |
"train_batch_size": 8,
|
100 |
"trial_name": null,
|
101 |
"trial_params": null
|