tuanna08go
commited on
Training in progress, step 20, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272383d12a5fcad411136bd3480b5492d7b47c552d9193198d809ccad09c083f
|
3 |
size 83945296
|
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 sha256:3d3de87719046d7db032655bf20fc8f233fc9cf472e5d947cea652b71a0342ca
|
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 sha256:0dd2615c3a7785dc34bada6df898075780bad0f714cbf0fd6866f9b4d0e65193
|
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 sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
|
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":
|
5 |
"eval_steps": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -46,6 +46,29 @@
|
|
46 |
"eval_samples_per_second": 18.46,
|
47 |
"eval_steps_per_second": 2.342,
|
48 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 10,
|
@@ -60,12 +83,12 @@
|
|
60 |
"should_evaluate": false,
|
61 |
"should_log": false,
|
62 |
"should_save": true,
|
63 |
-
"should_training_stop":
|
64 |
},
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
-
"total_flos":
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0125786163522013,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 18.46,
|
47 |
"eval_steps_per_second": 2.342,
|
48 |
"step": 12
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.8050314465408805,
|
52 |
+
"eval_loss": 0.003949903883039951,
|
53 |
+
"eval_runtime": 7.3201,
|
54 |
+
"eval_samples_per_second": 18.306,
|
55 |
+
"eval_steps_per_second": 2.322,
|
56 |
+
"step": 16
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.0125786163522013,
|
60 |
+
"grad_norm": 0.1989864557981491,
|
61 |
+
"learning_rate": 0.0,
|
62 |
+
"loss": 0.0158,
|
63 |
+
"step": 20
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.0125786163522013,
|
67 |
+
"eval_loss": 0.003575759707018733,
|
68 |
+
"eval_runtime": 7.2525,
|
69 |
+
"eval_samples_per_second": 18.476,
|
70 |
+
"eval_steps_per_second": 2.344,
|
71 |
+
"step": 20
|
72 |
}
|
73 |
],
|
74 |
"logging_steps": 10,
|
|
|
83 |
"should_evaluate": false,
|
84 |
"should_log": false,
|
85 |
"should_save": true,
|
86 |
+
"should_training_stop": true
|
87 |
},
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
+
"total_flos": 5.918605594066944e+16,
|
92 |
"train_batch_size": 8,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|