krishna-exe
commited on
Commit
•
8ad1e4c
1
Parent(s):
eddd5e1
End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8685015290519877,
|
4 |
+
"eval_loss": 0.34957513213157654,
|
5 |
+
"eval_runtime": 2.9329,
|
6 |
+
"eval_samples_per_second": 111.492,
|
7 |
+
"eval_steps_per_second": 3.751,
|
8 |
+
"total_flos": 2.2838958959910912e+17,
|
9 |
+
"train_loss": 0.41367715683536255,
|
10 |
+
"train_runtime": 173.7772,
|
11 |
+
"train_samples_per_second": 50.703,
|
12 |
+
"train_steps_per_second": 0.397
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8685015290519877,
|
4 |
+
"eval_loss": 0.34957513213157654,
|
5 |
+
"eval_runtime": 2.9329,
|
6 |
+
"eval_samples_per_second": 111.492,
|
7 |
+
"eval_steps_per_second": 3.751
|
8 |
+
}
|
runs/Oct10_10-50-21_e11ecca18f17/events.out.tfevents.1728558230.e11ecca18f17.609.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71202b6d1ff23ac2215ddd1db58895bf4708489cee9f13dc740c507a94a70115
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 2.2838958959910912e+17,
|
4 |
+
"train_loss": 0.41367715683536255,
|
5 |
+
"train_runtime": 173.7772,
|
6 |
+
"train_samples_per_second": 50.703,
|
7 |
+
"train_steps_per_second": 0.397
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8685015290519877,
|
3 |
+
"best_model_checkpoint": "brain-tumor-classification/checkpoint-69",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 69,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.43478260869565216,
|
13 |
+
"grad_norm": 7.908116340637207,
|
14 |
+
"learning_rate": 4.7580645161290326e-05,
|
15 |
+
"loss": 0.623,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.8695652173913043,
|
20 |
+
"grad_norm": 10.378320693969727,
|
21 |
+
"learning_rate": 3.951612903225806e-05,
|
22 |
+
"loss": 0.5239,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_accuracy": 0.7889908256880734,
|
28 |
+
"eval_loss": 0.5283120274543762,
|
29 |
+
"eval_runtime": 3.5122,
|
30 |
+
"eval_samples_per_second": 93.103,
|
31 |
+
"eval_steps_per_second": 3.132,
|
32 |
+
"step": 23
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.3043478260869565,
|
36 |
+
"grad_norm": 5.665172100067139,
|
37 |
+
"learning_rate": 3.1451612903225806e-05,
|
38 |
+
"loss": 0.4202,
|
39 |
+
"step": 30
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.7391304347826086,
|
43 |
+
"grad_norm": 9.73236083984375,
|
44 |
+
"learning_rate": 2.338709677419355e-05,
|
45 |
+
"loss": 0.3716,
|
46 |
+
"step": 40
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.0,
|
50 |
+
"eval_accuracy": 0.8409785932721713,
|
51 |
+
"eval_loss": 0.3933815658092499,
|
52 |
+
"eval_runtime": 2.873,
|
53 |
+
"eval_samples_per_second": 113.816,
|
54 |
+
"eval_steps_per_second": 3.829,
|
55 |
+
"step": 46
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.1739130434782608,
|
59 |
+
"grad_norm": 8.678784370422363,
|
60 |
+
"learning_rate": 1.5322580645161292e-05,
|
61 |
+
"loss": 0.3549,
|
62 |
+
"step": 50
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.608695652173913,
|
66 |
+
"grad_norm": 5.479146957397461,
|
67 |
+
"learning_rate": 7.258064516129033e-06,
|
68 |
+
"loss": 0.2964,
|
69 |
+
"step": 60
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 3.0,
|
73 |
+
"eval_accuracy": 0.8685015290519877,
|
74 |
+
"eval_loss": 0.34957513213157654,
|
75 |
+
"eval_runtime": 3.2055,
|
76 |
+
"eval_samples_per_second": 102.012,
|
77 |
+
"eval_steps_per_second": 3.432,
|
78 |
+
"step": 69
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 3.0,
|
82 |
+
"step": 69,
|
83 |
+
"total_flos": 2.2838958959910912e+17,
|
84 |
+
"train_loss": 0.41367715683536255,
|
85 |
+
"train_runtime": 173.7772,
|
86 |
+
"train_samples_per_second": 50.703,
|
87 |
+
"train_steps_per_second": 0.397
|
88 |
+
}
|
89 |
+
],
|
90 |
+
"logging_steps": 10,
|
91 |
+
"max_steps": 69,
|
92 |
+
"num_input_tokens_seen": 0,
|
93 |
+
"num_train_epochs": 3,
|
94 |
+
"save_steps": 500,
|
95 |
+
"stateful_callbacks": {
|
96 |
+
"TrainerControl": {
|
97 |
+
"args": {
|
98 |
+
"should_epoch_stop": false,
|
99 |
+
"should_evaluate": false,
|
100 |
+
"should_log": false,
|
101 |
+
"should_save": true,
|
102 |
+
"should_training_stop": true
|
103 |
+
},
|
104 |
+
"attributes": {}
|
105 |
+
}
|
106 |
+
},
|
107 |
+
"total_flos": 2.2838958959910912e+17,
|
108 |
+
"train_batch_size": 32,
|
109 |
+
"trial_name": null,
|
110 |
+
"trial_params": null
|
111 |
+
}
|