End of training
Browse files- README.md +3 -3
- all_results.json +16 -0
- eval_results.json +10 -0
- train_results.json +9 -0
- trainer_state.json +1185 -0
README.md
CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# silu-griffin-1024-c3t-8layer-simple_wikipedia_LM-vN
|
16 |
|
17 |
-
This model is a fine-tuned version of [silu-griffin-1024-c3t-8layer](https://huggingface.co/silu-griffin-1024-c3t-8layer) on
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 4.
|
20 |
-
- Accuracy: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
14 |
|
15 |
# silu-griffin-1024-c3t-8layer-simple_wikipedia_LM-vN
|
16 |
|
17 |
+
This model is a fine-tuned version of [silu-griffin-1024-c3t-8layer](https://huggingface.co/silu-griffin-1024-c3t-8layer) on the pszemraj/simple_wikipedia_LM dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 4.0476
|
20 |
+
- Accuracy: 0.4224
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.9972932091393998,
|
3 |
+
"eval_accuracy": 0.42241642228739,
|
4 |
+
"eval_loss": 4.047567367553711,
|
5 |
+
"eval_runtime": 14.4539,
|
6 |
+
"eval_samples": 250,
|
7 |
+
"eval_samples_per_second": 17.296,
|
8 |
+
"eval_steps_per_second": 4.359,
|
9 |
+
"perplexity": 57.25799982195849,
|
10 |
+
"total_flos": 6.247688798679859e+16,
|
11 |
+
"train_loss": 8.457253451250038,
|
12 |
+
"train_runtime": 65851.1603,
|
13 |
+
"train_samples": 50243,
|
14 |
+
"train_samples_per_second": 1.526,
|
15 |
+
"train_steps_per_second": 0.012
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.9972932091393998,
|
3 |
+
"eval_accuracy": 0.42241642228739,
|
4 |
+
"eval_loss": 4.047567367553711,
|
5 |
+
"eval_runtime": 14.4539,
|
6 |
+
"eval_samples": 250,
|
7 |
+
"eval_samples_per_second": 17.296,
|
8 |
+
"eval_steps_per_second": 4.359,
|
9 |
+
"perplexity": 57.25799982195849
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.9972932091393998,
|
3 |
+
"total_flos": 6.247688798679859e+16,
|
4 |
+
"train_loss": 8.457253451250038,
|
5 |
+
"train_runtime": 65851.1603,
|
6 |
+
"train_samples": 50243,
|
7 |
+
"train_samples_per_second": 1.526,
|
8 |
+
"train_steps_per_second": 0.012
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9972932091393998,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 784,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.012737839344001274,
|
13 |
+
"grad_norm": 7.091875076293945,
|
14 |
+
"learning_rate": 3.75e-05,
|
15 |
+
"loss": 37.744,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.02547567868800255,
|
20 |
+
"grad_norm": 2.930401563644409,
|
21 |
+
"learning_rate": 7.5e-05,
|
22 |
+
"loss": 34.0864,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.03821351803200382,
|
27 |
+
"grad_norm": 1.8477588891983032,
|
28 |
+
"learning_rate": 0.0001125,
|
29 |
+
"loss": 31.2726,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0509513573760051,
|
34 |
+
"grad_norm": 1.3455390930175781,
|
35 |
+
"learning_rate": 0.00015,
|
36 |
+
"loss": 28.3763,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.06368919672000636,
|
41 |
+
"grad_norm": 1.138717532157898,
|
42 |
+
"learning_rate": 0.00018749999999999998,
|
43 |
+
"loss": 26.957,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.07642703606400764,
|
48 |
+
"grad_norm": 0.9747544527053833,
|
49 |
+
"learning_rate": 0.000225,
|
50 |
+
"loss": 24.4616,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.08916487540800892,
|
55 |
+
"grad_norm": 0.9035225510597229,
|
56 |
+
"learning_rate": 0.0002625,
|
57 |
+
"loss": 22.5748,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.1019027147520102,
|
62 |
+
"grad_norm": 0.7786006927490234,
|
63 |
+
"learning_rate": 0.0003,
|
64 |
+
"loss": 20.6574,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.11464055409601147,
|
69 |
+
"grad_norm": 0.7649045586585999,
|
70 |
+
"learning_rate": 0.0003,
|
71 |
+
"loss": 18.9346,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.12737839344001273,
|
76 |
+
"grad_norm": 0.6415356993675232,
|
77 |
+
"learning_rate": 0.0003,
|
78 |
+
"loss": 17.8129,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.140116232784014,
|
83 |
+
"grad_norm": 0.5701594948768616,
|
84 |
+
"learning_rate": 0.0003,
|
85 |
+
"loss": 16.881,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.15285407212801527,
|
90 |
+
"grad_norm": 0.49638187885284424,
|
91 |
+
"learning_rate": 0.0003,
|
92 |
+
"loss": 16.2049,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.16559191147201657,
|
97 |
+
"grad_norm": 0.44346606731414795,
|
98 |
+
"learning_rate": 0.0003,
|
99 |
+
"loss": 15.9336,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.17832975081601785,
|
104 |
+
"grad_norm": 0.4194740355014801,
|
105 |
+
"learning_rate": 0.0003,
|
106 |
+
"loss": 15.2473,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.19106759016001912,
|
111 |
+
"grad_norm": 0.4130041301250458,
|
112 |
+
"learning_rate": 0.0003,
|
113 |
+
"loss": 15.1218,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.2038054295040204,
|
118 |
+
"grad_norm": 0.40480196475982666,
|
119 |
+
"learning_rate": 0.0003,
|
120 |
+
"loss": 14.7839,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.21654326884802166,
|
125 |
+
"grad_norm": 0.394378662109375,
|
126 |
+
"learning_rate": 0.0003,
|
127 |
+
"loss": 14.2312,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.22928110819202294,
|
132 |
+
"grad_norm": 0.39825204014778137,
|
133 |
+
"learning_rate": 0.0003,
|
134 |
+
"loss": 13.9441,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.2420189475360242,
|
139 |
+
"grad_norm": 0.38816991448402405,
|
140 |
+
"learning_rate": 0.0003,
|
141 |
+
"loss": 13.4799,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.25475678688002545,
|
146 |
+
"grad_norm": 0.36586159467697144,
|
147 |
+
"learning_rate": 0.0003,
|
148 |
+
"loss": 13.3276,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.25475678688002545,
|
153 |
+
"eval_accuracy": 0.013133919843597262,
|
154 |
+
"eval_loss": 12.040165901184082,
|
155 |
+
"eval_runtime": 14.4617,
|
156 |
+
"eval_samples_per_second": 17.287,
|
157 |
+
"eval_steps_per_second": 4.356,
|
158 |
+
"step": 100
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.26749462622402675,
|
162 |
+
"grad_norm": 0.40571218729019165,
|
163 |
+
"learning_rate": 0.0003,
|
164 |
+
"loss": 13.1015,
|
165 |
+
"step": 105
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.280232465568028,
|
169 |
+
"grad_norm": 0.3502795696258545,
|
170 |
+
"learning_rate": 0.0003,
|
171 |
+
"loss": 12.614,
|
172 |
+
"step": 110
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.2929703049120293,
|
176 |
+
"grad_norm": 0.33776018023490906,
|
177 |
+
"learning_rate": 0.0003,
|
178 |
+
"loss": 12.488,
|
179 |
+
"step": 115
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.30570814425603055,
|
183 |
+
"grad_norm": 0.3277961015701294,
|
184 |
+
"learning_rate": 0.0003,
|
185 |
+
"loss": 12.2282,
|
186 |
+
"step": 120
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.31844598360003185,
|
190 |
+
"grad_norm": 0.3399854898452759,
|
191 |
+
"learning_rate": 0.0003,
|
192 |
+
"loss": 12.0168,
|
193 |
+
"step": 125
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.33118382294403315,
|
197 |
+
"grad_norm": 0.31557145714759827,
|
198 |
+
"learning_rate": 0.0003,
|
199 |
+
"loss": 11.832,
|
200 |
+
"step": 130
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.3439216622880344,
|
204 |
+
"grad_norm": 0.32902857661247253,
|
205 |
+
"learning_rate": 0.0003,
|
206 |
+
"loss": 11.4818,
|
207 |
+
"step": 135
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.3566595016320357,
|
211 |
+
"grad_norm": 0.34518980979919434,
|
212 |
+
"learning_rate": 0.0003,
|
213 |
+
"loss": 11.3197,
|
214 |
+
"step": 140
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.36939734097603694,
|
218 |
+
"grad_norm": 0.32530176639556885,
|
219 |
+
"learning_rate": 0.0003,
|
220 |
+
"loss": 11.0346,
|
221 |
+
"step": 145
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.38213518032003824,
|
225 |
+
"grad_norm": 0.3253624141216278,
|
226 |
+
"learning_rate": 0.0003,
|
227 |
+
"loss": 10.6717,
|
228 |
+
"step": 150
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.3948730196640395,
|
232 |
+
"grad_norm": 0.33527347445487976,
|
233 |
+
"learning_rate": 0.0003,
|
234 |
+
"loss": 10.5302,
|
235 |
+
"step": 155
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.4076108590080408,
|
239 |
+
"grad_norm": 0.3164774477481842,
|
240 |
+
"learning_rate": 0.0003,
|
241 |
+
"loss": 10.2009,
|
242 |
+
"step": 160
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.420348698352042,
|
246 |
+
"grad_norm": 0.3047502934932709,
|
247 |
+
"learning_rate": 0.0003,
|
248 |
+
"loss": 10.1689,
|
249 |
+
"step": 165
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.4330865376960433,
|
253 |
+
"grad_norm": 0.31613191962242126,
|
254 |
+
"learning_rate": 0.0003,
|
255 |
+
"loss": 9.85,
|
256 |
+
"step": 170
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.4458243770400446,
|
260 |
+
"grad_norm": 0.3114412724971771,
|
261 |
+
"learning_rate": 0.0003,
|
262 |
+
"loss": 9.6662,
|
263 |
+
"step": 175
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.4585622163840459,
|
267 |
+
"grad_norm": 0.31863468885421753,
|
268 |
+
"learning_rate": 0.0003,
|
269 |
+
"loss": 9.4857,
|
270 |
+
"step": 180
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.4713000557280471,
|
274 |
+
"grad_norm": 0.3024883568286896,
|
275 |
+
"learning_rate": 0.0003,
|
276 |
+
"loss": 9.2409,
|
277 |
+
"step": 185
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.4840378950720484,
|
281 |
+
"grad_norm": 0.3118532598018646,
|
282 |
+
"learning_rate": 0.0003,
|
283 |
+
"loss": 9.156,
|
284 |
+
"step": 190
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.49677573441604966,
|
288 |
+
"grad_norm": 0.3026701807975769,
|
289 |
+
"learning_rate": 0.0003,
|
290 |
+
"loss": 9.0273,
|
291 |
+
"step": 195
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.5095135737600509,
|
295 |
+
"grad_norm": 0.3058376908302307,
|
296 |
+
"learning_rate": 0.0003,
|
297 |
+
"loss": 8.9207,
|
298 |
+
"step": 200
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.5095135737600509,
|
302 |
+
"eval_accuracy": 0.03601173020527859,
|
303 |
+
"eval_loss": 8.031224250793457,
|
304 |
+
"eval_runtime": 14.6886,
|
305 |
+
"eval_samples_per_second": 17.02,
|
306 |
+
"eval_steps_per_second": 4.289,
|
307 |
+
"step": 200
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.5222514131040522,
|
311 |
+
"grad_norm": 0.31776145100593567,
|
312 |
+
"learning_rate": 0.0003,
|
313 |
+
"loss": 8.819,
|
314 |
+
"step": 205
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.5349892524480535,
|
318 |
+
"grad_norm": 0.3050650656223297,
|
319 |
+
"learning_rate": 0.0003,
|
320 |
+
"loss": 8.7563,
|
321 |
+
"step": 210
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.5477270917920548,
|
325 |
+
"grad_norm": 0.31346216797828674,
|
326 |
+
"learning_rate": 0.0003,
|
327 |
+
"loss": 8.4781,
|
328 |
+
"step": 215
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.560464931136056,
|
332 |
+
"grad_norm": 0.3162192404270172,
|
333 |
+
"learning_rate": 0.0003,
|
334 |
+
"loss": 8.49,
|
335 |
+
"step": 220
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.5732027704800573,
|
339 |
+
"grad_norm": 0.2908290922641754,
|
340 |
+
"learning_rate": 0.0003,
|
341 |
+
"loss": 8.1487,
|
342 |
+
"step": 225
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.5859406098240586,
|
346 |
+
"grad_norm": 0.29553738236427307,
|
347 |
+
"learning_rate": 0.0003,
|
348 |
+
"loss": 8.2668,
|
349 |
+
"step": 230
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.5986784491680599,
|
353 |
+
"grad_norm": 0.288335919380188,
|
354 |
+
"learning_rate": 0.0003,
|
355 |
+
"loss": 8.1061,
|
356 |
+
"step": 235
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.6114162885120611,
|
360 |
+
"grad_norm": 0.30966615676879883,
|
361 |
+
"learning_rate": 0.0003,
|
362 |
+
"loss": 8.1297,
|
363 |
+
"step": 240
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.6241541278560624,
|
367 |
+
"grad_norm": 0.29941117763519287,
|
368 |
+
"learning_rate": 0.0003,
|
369 |
+
"loss": 7.8082,
|
370 |
+
"step": 245
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.6368919672000637,
|
374 |
+
"grad_norm": 0.29136765003204346,
|
375 |
+
"learning_rate": 0.0003,
|
376 |
+
"loss": 7.937,
|
377 |
+
"step": 250
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.649629806544065,
|
381 |
+
"grad_norm": 0.30150941014289856,
|
382 |
+
"learning_rate": 0.0003,
|
383 |
+
"loss": 7.7454,
|
384 |
+
"step": 255
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.6623676458880663,
|
388 |
+
"grad_norm": 0.28709036111831665,
|
389 |
+
"learning_rate": 0.0003,
|
390 |
+
"loss": 7.8069,
|
391 |
+
"step": 260
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.6751054852320675,
|
395 |
+
"grad_norm": 0.31939393281936646,
|
396 |
+
"learning_rate": 0.0003,
|
397 |
+
"loss": 7.631,
|
398 |
+
"step": 265
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.6878433245760688,
|
402 |
+
"grad_norm": 0.29692211747169495,
|
403 |
+
"learning_rate": 0.0003,
|
404 |
+
"loss": 7.6632,
|
405 |
+
"step": 270
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.7005811639200701,
|
409 |
+
"grad_norm": 0.3304164409637451,
|
410 |
+
"learning_rate": 0.0003,
|
411 |
+
"loss": 7.4727,
|
412 |
+
"step": 275
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.7133190032640714,
|
416 |
+
"grad_norm": 0.28332462906837463,
|
417 |
+
"learning_rate": 0.0003,
|
418 |
+
"loss": 7.4796,
|
419 |
+
"step": 280
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.7260568426080726,
|
423 |
+
"grad_norm": 0.2897827625274658,
|
424 |
+
"learning_rate": 0.0003,
|
425 |
+
"loss": 7.5389,
|
426 |
+
"step": 285
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 0.7387946819520739,
|
430 |
+
"grad_norm": 0.2887686491012573,
|
431 |
+
"learning_rate": 0.0003,
|
432 |
+
"loss": 7.382,
|
433 |
+
"step": 290
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.7515325212960752,
|
437 |
+
"grad_norm": 0.3093564212322235,
|
438 |
+
"learning_rate": 0.0003,
|
439 |
+
"loss": 7.2586,
|
440 |
+
"step": 295
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.7642703606400765,
|
444 |
+
"grad_norm": 0.2902717590332031,
|
445 |
+
"learning_rate": 0.0003,
|
446 |
+
"loss": 7.2681,
|
447 |
+
"step": 300
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.7642703606400765,
|
451 |
+
"eval_accuracy": 0.050643206256109484,
|
452 |
+
"eval_loss": 6.477533340454102,
|
453 |
+
"eval_runtime": 14.6327,
|
454 |
+
"eval_samples_per_second": 17.085,
|
455 |
+
"eval_steps_per_second": 4.305,
|
456 |
+
"step": 300
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.7770081999840777,
|
460 |
+
"grad_norm": 0.2867899239063263,
|
461 |
+
"learning_rate": 0.0003,
|
462 |
+
"loss": 7.0712,
|
463 |
+
"step": 305
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.789746039328079,
|
467 |
+
"grad_norm": 0.27321040630340576,
|
468 |
+
"learning_rate": 0.0003,
|
469 |
+
"loss": 7.0524,
|
470 |
+
"step": 310
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.8024838786720803,
|
474 |
+
"grad_norm": 0.3487064242362976,
|
475 |
+
"learning_rate": 0.0003,
|
476 |
+
"loss": 7.0939,
|
477 |
+
"step": 315
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.8152217180160816,
|
481 |
+
"grad_norm": 0.329608291387558,
|
482 |
+
"learning_rate": 0.0003,
|
483 |
+
"loss": 6.9997,
|
484 |
+
"step": 320
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.8279595573600828,
|
488 |
+
"grad_norm": 0.3154338300228119,
|
489 |
+
"learning_rate": 0.0003,
|
490 |
+
"loss": 6.9663,
|
491 |
+
"step": 325
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.840697396704084,
|
495 |
+
"grad_norm": 0.31021803617477417,
|
496 |
+
"learning_rate": 0.0003,
|
497 |
+
"loss": 6.7821,
|
498 |
+
"step": 330
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.8534352360480854,
|
502 |
+
"grad_norm": 0.388336181640625,
|
503 |
+
"learning_rate": 0.0003,
|
504 |
+
"loss": 6.7751,
|
505 |
+
"step": 335
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.8661730753920867,
|
509 |
+
"grad_norm": 0.31887954473495483,
|
510 |
+
"learning_rate": 0.0003,
|
511 |
+
"loss": 6.702,
|
512 |
+
"step": 340
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.8789109147360878,
|
516 |
+
"grad_norm": 0.31558957695961,
|
517 |
+
"learning_rate": 0.0003,
|
518 |
+
"loss": 6.6206,
|
519 |
+
"step": 345
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.8916487540800891,
|
523 |
+
"grad_norm": 0.30751529335975647,
|
524 |
+
"learning_rate": 0.0003,
|
525 |
+
"loss": 6.7077,
|
526 |
+
"step": 350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.9043865934240904,
|
530 |
+
"grad_norm": 0.33058232069015503,
|
531 |
+
"learning_rate": 0.0003,
|
532 |
+
"loss": 6.557,
|
533 |
+
"step": 355
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.9171244327680917,
|
537 |
+
"grad_norm": 0.3375111222267151,
|
538 |
+
"learning_rate": 0.0003,
|
539 |
+
"loss": 6.6369,
|
540 |
+
"step": 360
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.9298622721120929,
|
544 |
+
"grad_norm": 0.3047392964363098,
|
545 |
+
"learning_rate": 0.0003,
|
546 |
+
"loss": 6.5796,
|
547 |
+
"step": 365
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.9426001114560942,
|
551 |
+
"grad_norm": 0.430053174495697,
|
552 |
+
"learning_rate": 0.0003,
|
553 |
+
"loss": 6.5548,
|
554 |
+
"step": 370
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.9553379508000955,
|
558 |
+
"grad_norm": 0.3610515296459198,
|
559 |
+
"learning_rate": 0.0003,
|
560 |
+
"loss": 6.4576,
|
561 |
+
"step": 375
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.9680757901440968,
|
565 |
+
"grad_norm": 0.32095110416412354,
|
566 |
+
"learning_rate": 0.0003,
|
567 |
+
"loss": 6.4266,
|
568 |
+
"step": 380
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.980813629488098,
|
572 |
+
"grad_norm": 0.32170969247817993,
|
573 |
+
"learning_rate": 0.0003,
|
574 |
+
"loss": 6.5597,
|
575 |
+
"step": 385
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.9935514688320993,
|
579 |
+
"grad_norm": 0.29942792654037476,
|
580 |
+
"learning_rate": 0.0003,
|
581 |
+
"loss": 6.3873,
|
582 |
+
"step": 390
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 1.0062893081761006,
|
586 |
+
"grad_norm": 0.2971299886703491,
|
587 |
+
"learning_rate": 0.0003,
|
588 |
+
"loss": 6.3915,
|
589 |
+
"step": 395
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 1.0190271475201018,
|
593 |
+
"grad_norm": 0.2800815999507904,
|
594 |
+
"learning_rate": 0.0003,
|
595 |
+
"loss": 6.3187,
|
596 |
+
"step": 400
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 1.0190271475201018,
|
600 |
+
"eval_accuracy": 0.0433822091886608,
|
601 |
+
"eval_loss": 5.622740268707275,
|
602 |
+
"eval_runtime": 14.4103,
|
603 |
+
"eval_samples_per_second": 17.349,
|
604 |
+
"eval_steps_per_second": 4.372,
|
605 |
+
"step": 400
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.0317649868641032,
|
609 |
+
"grad_norm": 0.28819501399993896,
|
610 |
+
"learning_rate": 0.0003,
|
611 |
+
"loss": 6.328,
|
612 |
+
"step": 405
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.0445028262081044,
|
616 |
+
"grad_norm": 0.3983236849308014,
|
617 |
+
"learning_rate": 0.0003,
|
618 |
+
"loss": 6.3988,
|
619 |
+
"step": 410
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.0572406655521058,
|
623 |
+
"grad_norm": 0.2969406545162201,
|
624 |
+
"learning_rate": 0.0003,
|
625 |
+
"loss": 6.2509,
|
626 |
+
"step": 415
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.069978504896107,
|
630 |
+
"grad_norm": 0.2973212003707886,
|
631 |
+
"learning_rate": 0.0003,
|
632 |
+
"loss": 6.1234,
|
633 |
+
"step": 420
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.0827163442401082,
|
637 |
+
"grad_norm": 0.3298945426940918,
|
638 |
+
"learning_rate": 0.0003,
|
639 |
+
"loss": 6.3219,
|
640 |
+
"step": 425
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.0954541835841096,
|
644 |
+
"grad_norm": 0.3493943214416504,
|
645 |
+
"learning_rate": 0.0003,
|
646 |
+
"loss": 6.0888,
|
647 |
+
"step": 430
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.1081920229281108,
|
651 |
+
"grad_norm": 0.3639209270477295,
|
652 |
+
"learning_rate": 0.0003,
|
653 |
+
"loss": 6.2226,
|
654 |
+
"step": 435
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 1.120929862272112,
|
658 |
+
"grad_norm": 0.43913957476615906,
|
659 |
+
"learning_rate": 0.0003,
|
660 |
+
"loss": 6.0308,
|
661 |
+
"step": 440
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 1.1336677016161134,
|
665 |
+
"grad_norm": 0.43267834186553955,
|
666 |
+
"learning_rate": 0.0003,
|
667 |
+
"loss": 6.0806,
|
668 |
+
"step": 445
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.1464055409601146,
|
672 |
+
"grad_norm": 0.4563148021697998,
|
673 |
+
"learning_rate": 0.0003,
|
674 |
+
"loss": 5.9703,
|
675 |
+
"step": 450
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 1.159143380304116,
|
679 |
+
"grad_norm": 0.4002761244773865,
|
680 |
+
"learning_rate": 0.0003,
|
681 |
+
"loss": 5.9163,
|
682 |
+
"step": 455
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 1.1718812196481172,
|
686 |
+
"grad_norm": 0.4359826147556305,
|
687 |
+
"learning_rate": 0.0003,
|
688 |
+
"loss": 5.8285,
|
689 |
+
"step": 460
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.1846190589921184,
|
693 |
+
"grad_norm": 0.5450247526168823,
|
694 |
+
"learning_rate": 0.0003,
|
695 |
+
"loss": 5.8063,
|
696 |
+
"step": 465
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.1973568983361198,
|
700 |
+
"grad_norm": 0.3597274422645569,
|
701 |
+
"learning_rate": 0.0003,
|
702 |
+
"loss": 5.6978,
|
703 |
+
"step": 470
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 1.210094737680121,
|
707 |
+
"grad_norm": 0.4141215980052948,
|
708 |
+
"learning_rate": 0.0003,
|
709 |
+
"loss": 5.6078,
|
710 |
+
"step": 475
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 1.2228325770241222,
|
714 |
+
"grad_norm": 0.3695543110370636,
|
715 |
+
"learning_rate": 0.0003,
|
716 |
+
"loss": 5.6728,
|
717 |
+
"step": 480
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 1.2355704163681236,
|
721 |
+
"grad_norm": 0.5060051083564758,
|
722 |
+
"learning_rate": 0.0003,
|
723 |
+
"loss": 5.6049,
|
724 |
+
"step": 485
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 1.2483082557121248,
|
728 |
+
"grad_norm": 0.5355808138847351,
|
729 |
+
"learning_rate": 0.0003,
|
730 |
+
"loss": 5.6564,
|
731 |
+
"step": 490
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 1.261046095056126,
|
735 |
+
"grad_norm": 0.4578459858894348,
|
736 |
+
"learning_rate": 0.0003,
|
737 |
+
"loss": 5.5758,
|
738 |
+
"step": 495
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 1.2737839344001274,
|
742 |
+
"grad_norm": 0.4868403673171997,
|
743 |
+
"learning_rate": 0.0003,
|
744 |
+
"loss": 5.5695,
|
745 |
+
"step": 500
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 1.2737839344001274,
|
749 |
+
"eval_accuracy": 0.36348778103616813,
|
750 |
+
"eval_loss": 4.77961540222168,
|
751 |
+
"eval_runtime": 14.5581,
|
752 |
+
"eval_samples_per_second": 17.173,
|
753 |
+
"eval_steps_per_second": 4.328,
|
754 |
+
"step": 500
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 1.2865217737441286,
|
758 |
+
"grad_norm": 0.550255298614502,
|
759 |
+
"learning_rate": 0.0003,
|
760 |
+
"loss": 5.5591,
|
761 |
+
"step": 505
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 1.29925961308813,
|
765 |
+
"grad_norm": 0.5515110492706299,
|
766 |
+
"learning_rate": 0.0003,
|
767 |
+
"loss": 5.4588,
|
768 |
+
"step": 510
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 1.3119974524321312,
|
772 |
+
"grad_norm": 0.44656914472579956,
|
773 |
+
"learning_rate": 0.0003,
|
774 |
+
"loss": 5.4336,
|
775 |
+
"step": 515
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 1.3247352917761326,
|
779 |
+
"grad_norm": 0.5925999283790588,
|
780 |
+
"learning_rate": 0.0003,
|
781 |
+
"loss": 5.5185,
|
782 |
+
"step": 520
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 1.3374731311201338,
|
786 |
+
"grad_norm": 0.632453203201294,
|
787 |
+
"learning_rate": 0.0003,
|
788 |
+
"loss": 5.325,
|
789 |
+
"step": 525
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 1.350210970464135,
|
793 |
+
"grad_norm": 0.5380024909973145,
|
794 |
+
"learning_rate": 0.0003,
|
795 |
+
"loss": 5.4005,
|
796 |
+
"step": 530
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 1.3629488098081364,
|
800 |
+
"grad_norm": 0.5659191012382507,
|
801 |
+
"learning_rate": 0.0003,
|
802 |
+
"loss": 5.3564,
|
803 |
+
"step": 535
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 1.3756866491521376,
|
807 |
+
"grad_norm": 0.8913821578025818,
|
808 |
+
"learning_rate": 0.0003,
|
809 |
+
"loss": 5.2763,
|
810 |
+
"step": 540
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 1.3884244884961388,
|
814 |
+
"grad_norm": 0.9271002411842346,
|
815 |
+
"learning_rate": 0.0003,
|
816 |
+
"loss": 5.4129,
|
817 |
+
"step": 545
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 1.4011623278401402,
|
821 |
+
"grad_norm": 0.7141408324241638,
|
822 |
+
"learning_rate": 0.0003,
|
823 |
+
"loss": 5.4437,
|
824 |
+
"step": 550
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 1.4139001671841414,
|
828 |
+
"grad_norm": 0.5360827445983887,
|
829 |
+
"learning_rate": 0.0003,
|
830 |
+
"loss": 5.3523,
|
831 |
+
"step": 555
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 1.4266380065281425,
|
835 |
+
"grad_norm": 0.6563194990158081,
|
836 |
+
"learning_rate": 0.0003,
|
837 |
+
"loss": 5.1103,
|
838 |
+
"step": 560
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 1.439375845872144,
|
842 |
+
"grad_norm": 0.6325790882110596,
|
843 |
+
"learning_rate": 0.0003,
|
844 |
+
"loss": 5.4026,
|
845 |
+
"step": 565
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 1.4521136852161451,
|
849 |
+
"grad_norm": 0.8463213443756104,
|
850 |
+
"learning_rate": 0.0003,
|
851 |
+
"loss": 5.3129,
|
852 |
+
"step": 570
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 1.4648515245601466,
|
856 |
+
"grad_norm": 0.8394812345504761,
|
857 |
+
"learning_rate": 0.0003,
|
858 |
+
"loss": 5.3415,
|
859 |
+
"step": 575
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 1.4775893639041477,
|
863 |
+
"grad_norm": 0.692244291305542,
|
864 |
+
"learning_rate": 0.0003,
|
865 |
+
"loss": 5.2649,
|
866 |
+
"step": 580
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 1.4903272032481492,
|
870 |
+
"grad_norm": 0.6197806000709534,
|
871 |
+
"learning_rate": 0.0003,
|
872 |
+
"loss": 5.112,
|
873 |
+
"step": 585
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 1.5030650425921503,
|
877 |
+
"grad_norm": 0.6573797464370728,
|
878 |
+
"learning_rate": 0.0003,
|
879 |
+
"loss": 5.1669,
|
880 |
+
"step": 590
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 1.5158028819361515,
|
884 |
+
"grad_norm": 0.795892059803009,
|
885 |
+
"learning_rate": 0.0003,
|
886 |
+
"loss": 5.1693,
|
887 |
+
"step": 595
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 1.528540721280153,
|
891 |
+
"grad_norm": 0.6279253363609314,
|
892 |
+
"learning_rate": 0.0003,
|
893 |
+
"loss": 5.2926,
|
894 |
+
"step": 600
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 1.528540721280153,
|
898 |
+
"eval_accuracy": 0.3952492668621701,
|
899 |
+
"eval_loss": 4.392324447631836,
|
900 |
+
"eval_runtime": 14.409,
|
901 |
+
"eval_samples_per_second": 17.35,
|
902 |
+
"eval_steps_per_second": 4.372,
|
903 |
+
"step": 600
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 1.5412785606241541,
|
907 |
+
"grad_norm": 0.5762287378311157,
|
908 |
+
"learning_rate": 0.0003,
|
909 |
+
"loss": 5.0475,
|
910 |
+
"step": 605
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 1.5540163999681553,
|
914 |
+
"grad_norm": 0.5149503350257874,
|
915 |
+
"learning_rate": 0.0003,
|
916 |
+
"loss": 5.1185,
|
917 |
+
"step": 610
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 1.5667542393121567,
|
921 |
+
"grad_norm": 0.581633985042572,
|
922 |
+
"learning_rate": 0.0003,
|
923 |
+
"loss": 5.1166,
|
924 |
+
"step": 615
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 1.579492078656158,
|
928 |
+
"grad_norm": 0.5910624861717224,
|
929 |
+
"learning_rate": 0.0003,
|
930 |
+
"loss": 4.9907,
|
931 |
+
"step": 620
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 1.5922299180001591,
|
935 |
+
"grad_norm": 0.8280585408210754,
|
936 |
+
"learning_rate": 0.0003,
|
937 |
+
"loss": 5.0748,
|
938 |
+
"step": 625
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 1.6049677573441605,
|
942 |
+
"grad_norm": 0.5128599405288696,
|
943 |
+
"learning_rate": 0.0003,
|
944 |
+
"loss": 4.9768,
|
945 |
+
"step": 630
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 1.6177055966881617,
|
949 |
+
"grad_norm": 0.7540919184684753,
|
950 |
+
"learning_rate": 0.0003,
|
951 |
+
"loss": 5.0806,
|
952 |
+
"step": 635
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 1.630443436032163,
|
956 |
+
"grad_norm": 0.6239334940910339,
|
957 |
+
"learning_rate": 0.0003,
|
958 |
+
"loss": 5.1277,
|
959 |
+
"step": 640
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 1.6431812753761643,
|
963 |
+
"grad_norm": 0.7787991166114807,
|
964 |
+
"learning_rate": 0.0003,
|
965 |
+
"loss": 5.0778,
|
966 |
+
"step": 645
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 1.6559191147201657,
|
970 |
+
"grad_norm": 0.6328299641609192,
|
971 |
+
"learning_rate": 0.0003,
|
972 |
+
"loss": 4.9763,
|
973 |
+
"step": 650
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 1.668656954064167,
|
977 |
+
"grad_norm": 0.5455794334411621,
|
978 |
+
"learning_rate": 0.0003,
|
979 |
+
"loss": 5.0049,
|
980 |
+
"step": 655
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 1.681394793408168,
|
984 |
+
"grad_norm": 0.7078703045845032,
|
985 |
+
"learning_rate": 0.0003,
|
986 |
+
"loss": 5.0258,
|
987 |
+
"step": 660
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 1.6941326327521695,
|
991 |
+
"grad_norm": 0.6339858770370483,
|
992 |
+
"learning_rate": 0.0003,
|
993 |
+
"loss": 5.1028,
|
994 |
+
"step": 665
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 1.7068704720961707,
|
998 |
+
"grad_norm": 0.6060242652893066,
|
999 |
+
"learning_rate": 0.0003,
|
1000 |
+
"loss": 5.0428,
|
1001 |
+
"step": 670
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 1.719608311440172,
|
1005 |
+
"grad_norm": 0.9218889474868774,
|
1006 |
+
"learning_rate": 0.0003,
|
1007 |
+
"loss": 4.9891,
|
1008 |
+
"step": 675
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 1.7323461507841733,
|
1012 |
+
"grad_norm": 0.6890697479248047,
|
1013 |
+
"learning_rate": 0.0003,
|
1014 |
+
"loss": 4.8921,
|
1015 |
+
"step": 680
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 1.7450839901281745,
|
1019 |
+
"grad_norm": 0.9093934297561646,
|
1020 |
+
"learning_rate": 0.0003,
|
1021 |
+
"loss": 4.9385,
|
1022 |
+
"step": 685
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 1.7578218294721757,
|
1026 |
+
"grad_norm": 0.5929202437400818,
|
1027 |
+
"learning_rate": 0.0003,
|
1028 |
+
"loss": 4.9376,
|
1029 |
+
"step": 690
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 1.770559668816177,
|
1033 |
+
"grad_norm": 0.6317362189292908,
|
1034 |
+
"learning_rate": 0.0003,
|
1035 |
+
"loss": 4.9681,
|
1036 |
+
"step": 695
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 1.7832975081601783,
|
1040 |
+
"grad_norm": 0.5537763237953186,
|
1041 |
+
"learning_rate": 0.0003,
|
1042 |
+
"loss": 4.878,
|
1043 |
+
"step": 700
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 1.7832975081601783,
|
1047 |
+
"eval_accuracy": 0.40849266862170086,
|
1048 |
+
"eval_loss": 4.187656402587891,
|
1049 |
+
"eval_runtime": 14.4745,
|
1050 |
+
"eval_samples_per_second": 17.272,
|
1051 |
+
"eval_steps_per_second": 4.352,
|
1052 |
+
"step": 700
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.7960353475041795,
|
1056 |
+
"grad_norm": 0.5984592437744141,
|
1057 |
+
"learning_rate": 0.0003,
|
1058 |
+
"loss": 4.9092,
|
1059 |
+
"step": 705
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.808773186848181,
|
1063 |
+
"grad_norm": 0.5060558915138245,
|
1064 |
+
"learning_rate": 0.0003,
|
1065 |
+
"loss": 4.989,
|
1066 |
+
"step": 710
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 1.8215110261921823,
|
1070 |
+
"grad_norm": 0.8713288903236389,
|
1071 |
+
"learning_rate": 0.0003,
|
1072 |
+
"loss": 4.8114,
|
1073 |
+
"step": 715
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.8342488655361833,
|
1077 |
+
"grad_norm": 0.8011664748191833,
|
1078 |
+
"learning_rate": 0.0003,
|
1079 |
+
"loss": 4.8468,
|
1080 |
+
"step": 720
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 1.8469867048801847,
|
1084 |
+
"grad_norm": 0.6774628758430481,
|
1085 |
+
"learning_rate": 0.0003,
|
1086 |
+
"loss": 4.8899,
|
1087 |
+
"step": 725
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.859724544224186,
|
1091 |
+
"grad_norm": 1.05668044090271,
|
1092 |
+
"learning_rate": 0.0003,
|
1093 |
+
"loss": 4.8676,
|
1094 |
+
"step": 730
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.8724623835681873,
|
1098 |
+
"grad_norm": 0.8638430237770081,
|
1099 |
+
"learning_rate": 0.0003,
|
1100 |
+
"loss": 4.8515,
|
1101 |
+
"step": 735
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.8852002229121885,
|
1105 |
+
"grad_norm": 0.8210180997848511,
|
1106 |
+
"learning_rate": 0.0003,
|
1107 |
+
"loss": 4.9094,
|
1108 |
+
"step": 740
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 1.8979380622561899,
|
1112 |
+
"grad_norm": 0.6894564032554626,
|
1113 |
+
"learning_rate": 0.0003,
|
1114 |
+
"loss": 4.8406,
|
1115 |
+
"step": 745
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.910675901600191,
|
1119 |
+
"grad_norm": 0.7244303822517395,
|
1120 |
+
"learning_rate": 0.0003,
|
1121 |
+
"loss": 4.8299,
|
1122 |
+
"step": 750
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 1.9234137409441923,
|
1126 |
+
"grad_norm": 0.5788025856018066,
|
1127 |
+
"learning_rate": 0.0003,
|
1128 |
+
"loss": 4.8843,
|
1129 |
+
"step": 755
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.9361515802881937,
|
1133 |
+
"grad_norm": 0.5082942843437195,
|
1134 |
+
"learning_rate": 0.0003,
|
1135 |
+
"loss": 4.7624,
|
1136 |
+
"step": 760
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.9488894196321949,
|
1140 |
+
"grad_norm": 0.6290297508239746,
|
1141 |
+
"learning_rate": 0.0003,
|
1142 |
+
"loss": 4.7709,
|
1143 |
+
"step": 765
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.961627258976196,
|
1147 |
+
"grad_norm": 0.5582670569419861,
|
1148 |
+
"learning_rate": 0.0003,
|
1149 |
+
"loss": 4.7169,
|
1150 |
+
"step": 770
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.9743650983201975,
|
1154 |
+
"grad_norm": 0.6051950454711914,
|
1155 |
+
"learning_rate": 0.0003,
|
1156 |
+
"loss": 4.7701,
|
1157 |
+
"step": 775
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 1.9871029376641989,
|
1161 |
+
"grad_norm": 0.6427810788154602,
|
1162 |
+
"learning_rate": 0.0003,
|
1163 |
+
"loss": 4.7729,
|
1164 |
+
"step": 780
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.9972932091393998,
|
1168 |
+
"step": 784,
|
1169 |
+
"total_flos": 6.247688798679859e+16,
|
1170 |
+
"train_loss": 8.457253451250038,
|
1171 |
+
"train_runtime": 65851.1603,
|
1172 |
+
"train_samples_per_second": 1.526,
|
1173 |
+
"train_steps_per_second": 0.012
|
1174 |
+
}
|
1175 |
+
],
|
1176 |
+
"logging_steps": 5,
|
1177 |
+
"max_steps": 784,
|
1178 |
+
"num_input_tokens_seen": 0,
|
1179 |
+
"num_train_epochs": 2,
|
1180 |
+
"save_steps": 100,
|
1181 |
+
"total_flos": 6.247688798679859e+16,
|
1182 |
+
"train_batch_size": 4,
|
1183 |
+
"trial_name": null,
|
1184 |
+
"trial_params": null
|
1185 |
+
}
|