End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +99 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.4722222222222223,
|
3 |
+
"eval_accuracy": 0.9375,
|
4 |
+
"eval_loss": 0.23394718766212463,
|
5 |
+
"eval_runtime": 86.857,
|
6 |
+
"eval_samples_per_second": 0.368,
|
7 |
+
"eval_steps_per_second": 0.046
|
8 |
+
}
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.4722222222222223,
|
3 |
+
"eval_accuracy": 0.9375,
|
4 |
+
"eval_loss": 0.23394718766212463,
|
5 |
+
"eval_runtime": 86.857,
|
6 |
+
"eval_samples_per_second": 0.368,
|
7 |
+
"eval_steps_per_second": 0.046
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8181818181818182,
|
3 |
+
"best_model_checkpoint": "videomae-base-finetuned-HumanActivityRecognition/checkpoint-36",
|
4 |
+
"epoch": 1.4722222222222223,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2777777777777778,
|
13 |
+
"grad_norm": 5.786031246185303,
|
14 |
+
"learning_rate": 4.0625000000000005e-05,
|
15 |
+
"loss": 0.6663,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5277777777777778,
|
20 |
+
"eval_accuracy": 0.7575757575757576,
|
21 |
+
"eval_loss": 0.6102488040924072,
|
22 |
+
"eval_runtime": 88.7114,
|
23 |
+
"eval_samples_per_second": 0.372,
|
24 |
+
"eval_steps_per_second": 0.056,
|
25 |
+
"step": 19
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.0277777777777777,
|
29 |
+
"grad_norm": 4.736588478088379,
|
30 |
+
"learning_rate": 2.5e-05,
|
31 |
+
"loss": 0.5959,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.3055555555555556,
|
36 |
+
"grad_norm": 7.99476957321167,
|
37 |
+
"learning_rate": 9.375000000000001e-06,
|
38 |
+
"loss": 0.4422,
|
39 |
+
"step": 30
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.4722222222222223,
|
43 |
+
"eval_accuracy": 0.8181818181818182,
|
44 |
+
"eval_loss": 0.3773638606071472,
|
45 |
+
"eval_runtime": 85.8376,
|
46 |
+
"eval_samples_per_second": 0.384,
|
47 |
+
"eval_steps_per_second": 0.058,
|
48 |
+
"step": 36
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.4722222222222223,
|
52 |
+
"step": 36,
|
53 |
+
"total_flos": 3.576205371783905e+17,
|
54 |
+
"train_loss": 0.519466370344162,
|
55 |
+
"train_runtime": 2047.7986,
|
56 |
+
"train_samples_per_second": 0.141,
|
57 |
+
"train_steps_per_second": 0.018
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.4722222222222223,
|
61 |
+
"eval_accuracy": 0.9375,
|
62 |
+
"eval_loss": 0.23394717276096344,
|
63 |
+
"eval_runtime": 87.1014,
|
64 |
+
"eval_samples_per_second": 0.367,
|
65 |
+
"eval_steps_per_second": 0.046,
|
66 |
+
"step": 36
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.4722222222222223,
|
70 |
+
"eval_accuracy": 0.9375,
|
71 |
+
"eval_loss": 0.23394718766212463,
|
72 |
+
"eval_runtime": 86.857,
|
73 |
+
"eval_samples_per_second": 0.368,
|
74 |
+
"eval_steps_per_second": 0.046,
|
75 |
+
"step": 36
|
76 |
+
}
|
77 |
+
],
|
78 |
+
"logging_steps": 10,
|
79 |
+
"max_steps": 36,
|
80 |
+
"num_input_tokens_seen": 0,
|
81 |
+
"num_train_epochs": 9223372036854775807,
|
82 |
+
"save_steps": 500,
|
83 |
+
"stateful_callbacks": {
|
84 |
+
"TrainerControl": {
|
85 |
+
"args": {
|
86 |
+
"should_epoch_stop": false,
|
87 |
+
"should_evaluate": false,
|
88 |
+
"should_log": false,
|
89 |
+
"should_save": true,
|
90 |
+
"should_training_stop": true
|
91 |
+
},
|
92 |
+
"attributes": {}
|
93 |
+
}
|
94 |
+
},
|
95 |
+
"total_flos": 3.576205371783905e+17,
|
96 |
+
"train_batch_size": 8,
|
97 |
+
"trial_name": null,
|
98 |
+
"trial_params": null
|
99 |
+
}
|